AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions & skills before you clone — plus an always-on AI attack-signature scanner and native Rust & PHP rules. Also: medusa scan --git to vet any repo, medusa secrets scan for leaked API keys. 40,000+ patterns, zero setup.
MEDUSA is an AI-focused security scanner that examines source code, repositories, and developer histories for vulnerabilities, attack patterns, and exposed secrets. It is used to check AI applications, agents, MCP servers, traditional code, and Git repositories for security problems before deployment or sharing.
Latest release v2026.7.0 — MEDUSA v2026.7.0 · 24 Jun 2026
1 file for Claude Code: medusa CLAUDE.md — 2,806 tokens loaded in every session.
CLAUDE.md A 2,806 tok These files are Pantheon-Security/medusa's own configuration — they tell 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.