skills/agentskillexchange/skills/Scan agent repos for repo-poisoning, unsafe AI config files, and MCP attack surfaces with MEDUSA/Gen Agent Trust Hub
Scan agent repos for repo-poisoning, unsafe AI config files, and MCP attack surfaces with MEDUSA
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent or user to install the
medusa-securitypackage from PyPI and provides links to clone the tool's source code from GitHub (https://github.com/Pantheon-Security/medusa). - [NO_CODE]: The skill consists entirely of markdown documentation, metadata, and installation instructions. It does not provide any scripts, executables, or specific tool definitions for the agent to execute directly.
Audit Metadata