pr-babysitter
Warn
Audited by Snyk on May 17, 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 fetches and processes untrusted, user-generated content from GitHub (e.g., Phase 4 "Comment Check" in SKILL.md which fetches reviewThreads via the GraphQL query shown in references/github-api.md and processes issue/pr comments per references/bot-patterns.md), and it uses those comments to classify, generate fixes, and drive actions (commits, resolves, pushes), so third-party content can materially influence tool use and behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata