4-step-program
Warn
Audited by Snyk on Feb 25, 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 requires fetching and parsing GitHub issue and PR content (e.g., "Read the full issue:
gh issue view <number>", "gh pr view --json closingIssuesReferences", and creating PR reviews posted to GitHub), which are untrusted, user-generated third-party sources that the agent must interpret and that directly drive tooling decisions and next actions.
Audit Metadata