scholar-review

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text enters the LLM context via Read(reviewCommentsPath) in Phase 2 (reviewer comments are provided by the user as a path to external reviewer feedback), and that text is then preserved as originalText/Original and used in later phases’ rebuttal writing.