rebuttal
Warn
Audited by Snyk on May 13, 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). The skill explicitly ingests and verbatim-normalizes external reviewer content (Required Inputs: "Raw reviews — pasted text, markdown, or PDF with reviewer IDs" and Phase 1: "Normalize all reviewer text into rebuttal/REVIEWS_RAW.md (verbatim)"), which is untrusted user-generated third‑party content that the agent reads and uses to drive drafting and tool-driven decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata