babysit-loop
Warn
Audited by Snyk on Jul 30, 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). SKILL.md step 3/4 repeatedly reads outsider-authored pull request content (titles/bodies/reviews/diffs/comments) from the target repository’s PR queue and linked work item at runtime to compute eligibility and drive subagent/scoped invocations (via
/source-control:babysit-prs), so an outsider who can submit content to that PR stream can poison the workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata