full-send
Warn
Audited by Snyk on Nov 18, 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 required workflow reads outsider-authored GitHub PR titles, descriptions, review threads, comments, and review-bot output (via
gh pr viewandbabysit-pr) without the agent first selecting a specific item, so an outsider who comments on or opens a PR can deliver text into the agent's context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata