academic-paper

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

• Third-party content exposure detected (medium risk: 0.30). In agents/intake_agent → academic-paper pipeline Phase 0, the agent ingests the user’s free-text paper prompt/configuration via the “Configuration interview” (and optional style calibration) and the downstream phases then draft from that content, so outsider-authored text is directly consumed.