rebuttal

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

• Third-party content exposure detected (high risk: 0.70). The required runtime workflow preserves reviewer comments verbatim into .writing/reviews/REVIEWS_RAW.md (reviewer-authored free text provided by outside parties), and then drafts responses grounded in that text—so outsider free-form comment text can enter the LLM context via the review ingestion → draft path.