fact-check

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow can ingest outsider-authored free text because, in Phase 2 Step 1 and the report output, it uses “provided source documents” and (when missing) “reach[es] for the web”; any caller-supplied web pages/scraped text or outsider-written documents become readable prose in the LLM context.