Download
AI-Infra-Guard is an open-source AI red teaming platform for evaluating security risks across modern AI ecosystems. It combines scanning for AI agents, agent skills, MCP servers, AI infrastructure, and OpenClaw deployments. Its infrastructure scanner fingerprints AI services and checks them against a large library of known vulnerabilities. Agent and skill analysis detects risks involving malicious instructions, unsafe code execution, privilege abuse, compromised tools, and insecure dependencies. Jailbreak evaluation tests language models against multiple prompt-based attack methods and enables cross-model comparison. The platform also provides a web interface, standalone scanning tools, APIs, Docker deployment, and integrations for incorporating security checks into AI workflows.
Features
- AI agent security scanning
- MCP server and agent skill analysis
- AI infrastructure vulnerability detection
- LLM jailbreak and prompt security evaluation
- OpenClaw security assessment
- Web interface, APIs, and Docker deployment
Project Samples
