om-review-prs
Warn
Audited by Snyk on Aug 11, 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 SKILL.md step 1–4 the sweep uses the tracker operation
list-prsto ingest outsider-authored PR metadata (title, etc.) into the LLM’s runtime queue, and then step 5 delegates per-PR review toom-auto-review-prfor further processing—so an outsider can submit a PR with free-text fields that this workflow reads without first selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata