Spaces:
Running
Running
| title: CodeIntegrity | |
| emoji: 🛡️ | |
| colorFrom: blue | |
| colorTo: gray | |
| sdk: static | |
| pinned: false | |
| # CodeIntegrity | |
| CodeIntegrity secures endpoint AI agents and connected-tool execution. For supported agents, security teams can inspect configurations, skills, and session activity and apply configured policy before tool calls run. | |
| Our research covers indirect prompt injection, MCP tool poisoning, and agent skill supply chain risk. | |
| - [Product and runtime controls](https://www.codeintegrity.ai/product) | |
| - [Research and technical articles](https://www.codeintegrity.ai/blog) | |
| - [PromptGuard model](https://huggingface.co/codeintegrity-ai/promptguard) and [independent benchmark methods and results](https://www.codeintegrity.ai/benchmark) | |
| - [DERAIL prompt injection research](https://www.codeintegrity.ai/blog/derail) and [swarm poisoning research](https://www.codeintegrity.ai/blog/swarm-poisoning-agent-harnesses) | |
| - [CodeIntegrity's $5M seed round led by SYN Ventures](https://www.codeintegrity.ai/blog/codeintegrity-seed-round) | |