github-cli
Warn
Audited by Snyk on Feb 16, 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 explicitly fetches and displays user-generated, public GitHub content (e.g., gh issue view --comments, gh pr view / gh pr diff, and gh api repos/{owner}/{repo}/pulls/.../comments), so the agent will read untrusted third-party input that could contain indirect prompt injection.
Audit Metadata