Skill Detail

Scan repositories for AI supply-chain and agent-security risks with Medusa Security

Use Medusa Security before trusting a repository, dependency, or AI-agent codebase when an agent needs a focused scan for repo poisoning, prompt-injection, MCP, and AI supply-chain findings.

Security & VerificationMulti-Framework
Security & Verification Multi-Framework Security Reviewed
⭐ 256 GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill scan-repositories-for-ai-supply-chain-and-agent-security-risks-with-medusa-security Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Python 3.10+, pip, local repository path or remote Git URL
Install & setup
Install with pip install medusa-security, then run medusa scan against a local repository or use medusa scan –git <repo> to assess a remote repository before trusting it.
Author
Pantheon Security
Publisher
Organization
Last updated
Apr 20, 2026
Quick brief

Use Medusa Security when the agent needs a pre-trust repository scan focused on AI and agent attack surfaces. The tool is built around scanning codebases for repo poisoning, prompt-injection-related artifacts, MCP risks, AI supply-chain issues, and broader security findings with dedicated CLI workflows.

How it works

What this skill actually does

Invoke this instead of using the product normally when the task is to vet a repository before adoption, execution, or dependency approval. The operator workflow is specific: install Medusa, scan a local repo or a remote Git URL, then use the findings to decide whether the codebase is safe enough to trust or merge.

The scope boundary keeps it skill-shaped. This is not a generic security platform listing and not a broad package card. It is the bounded workflow of running an AI-focused repository security scan before trust, execution, or handoff.