scholar-rebuttal-pro

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text from the user-provided reviewer comments (file/inline/pasted text) is read at runtime in Phase 1 (Read(reviewCommentsPath) / inline reviewCommentsPath) and then injected into LLM context via ccw cli ... CONTEXT: @<review-file> and later reused in Phase 2/3/4 prompts.