academic-paper-reviewer

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests the submitted manuscript text into multiple reviewer agents (e.g., Phase 1 “Reads the complete paper” / “Full paper content”), and that manuscript is explicitly treated as untrusted input that can contain embedded instructions—i.e., outsider-authored free text (the author’s paper) flows into the LLM context.