review-core
Warn
Audited by Snyk on May 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs capturing "web.run" citations and URLs in Step 3 ("Capture Evidence") and the Evidence appendix, which indicates the agent will fetch and interpret third‑party web content that could materially influence review decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata