rebuttal
Warn
Audited by Snyk on May 18, 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). This skill explicitly loads and normalizes external "raw reviews" (pasted text, markdown, or PDF) into rebuttal/REVIEWS_RAW.md and then reads and acts on those reviewer texts throughout the workflow (Phase 0/1 and Phase 2–7), meaning untrusted reviewer/user-generated content from public review systems could materially influence tool decisions and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata