investigation
Warn
Audited by Snyk on Feb 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs cloning external package repositories for API review ("For external package API review: clone to scratch/repos/ for direct source access"), which requires fetching and reading public third‑party code/docs that the agent will interpret and could influence its actions.
Audit Metadata