academic-pipeline

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

• Third-party content exposure detected (high risk: 0.90). The skill's integrity_verification_agent explicitly performs WebSearch and Semantic Scholar API / DOI/publisher lookups to verify every reference and to trace claim sources (see agents/integrity_verification_agent.md Phase A: Existence Check / A0 Semantic Scholar API and Phase E: Source Tracing), and those public web results are ingested and used as blocking PASS/FAIL decisions that materially drive pipeline actions.