answer-engine-content-audit

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

• Third-party content exposure detected (high risk: 0.85). The required workflow (review homepage/product pages/docs/FAQs/policies/support content via runtime page fetching implied by the checks) ingests outsider-authored free text from public web pages into the agent’s LLM context during content inspection (e.g., fetched page HTML rendered to text/excerpts).