Datasets:

emgena
/

agent_env_file_plaintext_exfiltration_guard_teaser

⚡ Official Evaluation Teaser by Emgena AI Labs.
Contains 50 verified production trajectories for DevSecOps & Cloud Security.
👉 🚀 Hol dir das vollständige Turnkey-Paket (500 Samples + AST MCP Guard) direkt bei EMGENA AI Labs
(Gutscheincode LAUNCH20 für 20 € Direktrabatt & sofortigen Download)

🌟 Enterprise USP & Features

Detects unauthorized reading of .env, pem, and id_rsa files in coding agent tool calls, redacting secrets before prompt inclusion.

Deterministic In-IDE Guardrails: Validated across Cursor IDE and Claude Desktop.
100% AST Syntactic Validation (Zero Syntax Errors)
EU AI Act & EULA Compliance: Certified for enterprise deployment under Articles 50 & 53.

🎁 Full Enterprise MCP Suite

Die vollständige Version enthält 500 AST-geprüfte Trajektorien, 30 Produktions-Incidents, den Zero-Dependency MCP Server (server.py), DPO-Präferenzpaare und BGB/EU AI Act Compliance.

🛒 Vollständiges Paket kaufen: EMGENA AI Labs Store
🏷️ 20 € Rabatt-Gutschein: LAUNCH20
🌐 Offizieller Webshop: https://emgena.com/trainingslager

🛡️ MCP Quickstart (Free Community Edition)

# In Cursor oder Claude Desktop einbinden
python server_free.py

Verifiziert nach FAANG v2.5 Gold Standard von Emgena AI Labs.

Downloads last month: 98

Number of rows:

Total file size:

1.13 MB

id stringlengths 53 53	incident_id stringlengths 51 51	domain stringclasses 1 value	messages listlengths 5 5
agent_env_file_plaintext_exfiltration_guard_traj_0000	agent_env_file_plaintext_exfiltration_guard_inc_001	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0001	agent_env_file_plaintext_exfiltration_guard_inc_002	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0002	agent_env_file_plaintext_exfiltration_guard_inc_003	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0003	agent_env_file_plaintext_exfiltration_guard_inc_004	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0004	agent_env_file_plaintext_exfiltration_guard_inc_005	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0005	agent_env_file_plaintext_exfiltration_guard_inc_006	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0006	agent_env_file_plaintext_exfiltration_guard_inc_007	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0007	agent_env_file_plaintext_exfiltration_guard_inc_008	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0008	agent_env_file_plaintext_exfiltration_guard_inc_009	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0009	agent_env_file_plaintext_exfiltration_guard_inc_010	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0010	agent_env_file_plaintext_exfiltration_guard_inc_011	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0011	agent_env_file_plaintext_exfiltration_guard_inc_012	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0012	agent_env_file_plaintext_exfiltration_guard_inc_013	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0013	agent_env_file_plaintext_exfiltration_guard_inc_014	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0014	agent_env_file_plaintext_exfiltration_guard_inc_015	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0015	agent_env_file_plaintext_exfiltration_guard_inc_016	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0016	agent_env_file_plaintext_exfiltration_guard_inc_017	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0017	agent_env_file_plaintext_exfiltration_guard_inc_018	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0018	agent_env_file_plaintext_exfiltration_guard_inc_019	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0019	agent_env_file_plaintext_exfiltration_guard_inc_020	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0020	agent_env_file_plaintext_exfiltration_guard_inc_021	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0021	agent_env_file_plaintext_exfiltration_guard_inc_022	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0022	agent_env_file_plaintext_exfiltration_guard_inc_023	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0023	agent_env_file_plaintext_exfiltration_guard_inc_024	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0024	agent_env_file_plaintext_exfiltration_guard_inc_025	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0025	agent_env_file_plaintext_exfiltration_guard_inc_026	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0026	agent_env_file_plaintext_exfiltration_guard_inc_027	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0027	agent_env_file_plaintext_exfiltration_guard_inc_028	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0028	agent_env_file_plaintext_exfiltration_guard_inc_029	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0029	agent_env_file_plaintext_exfiltration_guard_inc_030	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0030	agent_env_file_plaintext_exfiltration_guard_inc_001	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0031	agent_env_file_plaintext_exfiltration_guard_inc_002	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0032	agent_env_file_plaintext_exfiltration_guard_inc_003	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0033	agent_env_file_plaintext_exfiltration_guard_inc_004	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0034	agent_env_file_plaintext_exfiltration_guard_inc_005	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0035	agent_env_file_plaintext_exfiltration_guard_inc_006	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...
agent_env_file_plaintext_exfiltration_guard_traj_0036	agent_env_file_plaintext_exfiltration_guard_inc_007	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are Emgena AI Labs Enterprise Sentinel for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Analyze production telemetry, trace defect root cause, invoke diagnostic tools, and deliver AST-validated zero-defect remediations." }, { ...
agent_env_file_plaintext_exfiltration_guard_traj_0037	agent_env_file_plaintext_exfiltration_guard_inc_008	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are the FAANG v2.5 Staff Reliability Architect specializing in IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Inspect runtime traces and execute strict AST static analysis guards to protect critical production infrastructure." }, ...
agent_env_file_plaintext_exfiltration_guard_traj_0038	agent_env_file_plaintext_exfiltration_guard_inc_009	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Autonomous AI Defense Guard for IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation. Enforce zero-tolerance safety policies, eliminate memory leaks and runtime deadlocks, and verify code invariance via AST parsing." }, { "rol...
agent_env_file_plaintext_exfiltration_guard_traj_0039	agent_env_file_plaintext_exfiltration_guard_inc_010	IDE Coding Agent Sandboxing, Destructive Command Interception & Workspace Isolation	[ { "role": "system", "content": "You are an Enterprise SRE Sentinel operating under strict EU AI Act compliance. Diagnose incidents, execute diagnostic tools, and output production-ready remediations." }, { "role": "user", "content": "CRITICAL PRODUCTION ALERT in service 'agent_env_file_plaintext...