pr-shepherd
Warn
Audited by Snyk on Aug 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s required workflow reads GitHub PR review comments/threads and other PR state via
gh pr view/gh pr checksand “Review comments” fetched fresh and fully paginated, so outsider-authored text in the PR conversation is ingested at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata