Audits AI agent skills for safety using static, semantic, adversarial, and supply-chain analysis, providing scores and risk flags. Can be run via CLI, CI, or as an MCP tool from Claude Code, Cursor, and Codex.
Provides code auditing tools including repository cloning, AST analysis, security scanning with Semgrep, and LLM-powered code explanations via the Model Context Protocol.
Security co-pilot for AI agents. Scans for vulnerabilities like prompt injection, infinite loops, and token bombing in AI Agents, audits MCP servers, verifies AGENTS.md governance, and generates EU AI Act compliance reports.
Vets MCP servers, Claude Code skills, or plugins for unsafe behavior like shell execution, secret access, data exfiltration, prompt injection, and remote code before installation, returning a graded verdict with findings.
Audits MCP tool descriptions for quality and reliability, scoring them 0-100, detecting smells, and providing rewritten versions for better agent accuracy.
