babysit-pr
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). In
scripts/threads.sh, the skill harvestsreviewThreads/comments(first.nodes[0].body/last.nodes[0].body) and top-level review/review-bodybodyfields from the target PR on GitHub/GitLab via authenticatedgh api/glab api, so outsider-authored PR review bot findings and related free text are ingested at runtime without needing to pre-select a specific text item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata