address-github-comments
Warn
Audited by Snyk on Feb 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: 0.90). This skill fetches and instructs the agent to read GitHub Pull Request comments via "gh pr view --comments" (user-generated content on GitHub), so it ingests untrusted third-party content as part of its workflow.
Audit Metadata