work-with-pr
Warn
Audited by Snyk on Mar 27, 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 parses untrusted, user-generated GitHub content (CI run logs via
gh run view --log-failedand PR review bodies viagh api "repos/${REPO}/pulls/${PR_NUMBER}/reviews", including Cubic and human reviewer comments) and then uses those text contents to decide fixes, commits, and next actions—allowing indirect injection via crafted review/comments or log output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata