academic-pipeline

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for Stage 2.5/4.5 calls integrity_verification_agent, which performs WebSearch/DOI lookups and ingests the resulting page/snippet text into the agent’s LLM context to verify references and claims (public web content fetched at runtime = outsider-authored free text).