Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Apple HIG reference and cross-framework UI audit tooling for agents.