code-review
Warn
Audited by Snyk on Apr 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes public GitHub PR content (e.g., "gh pr diff <PR_NUMBER>" and reading changed files via git/gh) which is user-generated/untrusted and the agent is expected to read that content and act on it (including posting comments), so third-party content can materially influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata