rebuttal

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and verbatim-normalizes "Raw reviews — pasted text, markdown, or PDF" (see "Required Inputs" and Phase 1: "Normalize all reviewer text into rebuttal/REVIEWS_RAW.md") and then reads and uses those reviewer comments to build issue boards, strategy plans, and draft rebuttals, so untrusted, user-generated reviewer content can directly influence tool decisions and actions.