Scan every AI agent skill on your machine for prompt injection and malicious code. Fast local rules by default, with optional local LLM review for deeper context.
Latest release v0.2.1 · 8 May 2026
2 files for Codex, OpenCode and Claude Code: skill-audit AGENTS.md, skill-audit CLAUDE.md — 3,423 tokens loaded in every session.
AGENTS.md A 997 tok CLAUDE.md A 2,426 tok These files are ondrej-merkun/skill-audit's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.