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.
Lint agent SKILL.md files and MCP tool schemas to catch issues like missing descriptions, similar skills, unconstrained parameters, and destructive tools without confirmation gates.
Enables deterministic auditing of agent skills, system prompts, and downloaded file collections against eight malicious-skill supply-chain patterns, returning line-numbered findings and pass/flag verdicts without using an LLM or network calls.
Enables AI coding agents to verify code against YAML specifications, detecting missing fields, extra fields, and type mismatches to prevent silent drift before commits.
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.
