github-address-comments
Warn
Audited by Snyk on Feb 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: 1.00). The skill's workflow explicitly fetches and ingests GitHub review threads and issue comments via scripts/fetch_review_threads.py (using the gh GraphQL API) and then requires the agent to read and act on those user-generated comments to prioritize fixes and make code/reply decisions, so untrusted third-party content can influence actions.
Audit Metadata