psychrev-rebuttal

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests reviewer letter/comments (outsider-authored free-form text) and instructs quoting them point-by-point in the response document, which would feed that free text into the agent’s LLM context via the “point-by-point, quoting each comment” runtime path.