review-pr
Warn
Audited by Snyk on Mar 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's workflow explicitly fetches and reads user-generated GitHub content (e.g.,
gh pr diff <number>,gh api "repos/$REPO/pulls/<number>/reviews", and issue comments viagh api "repos/$REPO/issues/<number>/comments"), so the agent ingests untrusted third-party PRs/comments and uses them to decide review actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata