resolve-pr-reviews
Warn
Audited by Snyk on Mar 8, 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 PR review threads from GitHub via the GraphQL query in Phase 2 and then reads and interprets reviewers' comment bodies (user-generated content) in Phase 3 to decide, implement, and commit code changes, so untrusted third-party comments can directly influence agent actions.
Audit Metadata