skills/agentskillexchange/skills/Scan agent repos for repo-poisoning, unsafe AI config files, and MCP attack surfaces with MEDUSA/Snyk
Scan agent repos for repo-poisoning, unsafe AI config files, and MCP attack surfaces with MEDUSA
Warn
Audited by Snyk on Oct 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow scans local or target GitHub repositories using MEDUSA, which reads external repository code and files authored by outsiders.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata