1k-code-review-pr
Warn
Audited by Snyk on Mar 10, 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 instructs the reviewer to fetch and read PR descriptions from GitHub (e.g., "gh pr view PRNUM --json body" in the Documentation/Checklist and Review Workflow), which is untrusted, user-generated third-party content that the agent is expected to interpret and use when forming review decisions.
Audit Metadata