listing-accuracy-audit

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow calls UnifAPI maps/search / local/search and seo/serp to ingest live public listing/SERP text (outsider-authored content from third-party map/SERP sources) into the agent’s LLM context for field-by-field comparison.