autonomous-review
Warn
Audited by Snyk on May 14, 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 mandatorily reads all issue and PR comments via GitHub CLI (e.g., "gh issue view ... --json comments" and extracting a preview URL from PR comments) and navigates to the extracted preview URL for E2E checks, which are untrusted, user-generated third‑party inputs that directly influence review decisions and automated actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata