ondrej-merkun/skill-audit

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.

This repository also configures its own agents. See what skill-audit tells them →

3Stars on the repository
3Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
customA LICENSE file GitHub cannot name, so bodies are not copied

skill-audit

01

ondrej-merkun/skill-audit

Skill Claude Code

Scan installed agent skills, plugins, and cross-agent instruction files for prompt injection, exfiltration, malicious code, and dependency risk. Use when the user asks to audit, check, review, inventory, or verify skills for Claude Code, Codex, Cursor, Copilot, Gemini, or AGENTS.md-style project instructions.

not rated 3 1mo ago A 70 tokens