llm-mention-tracking

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

• Third-party content exposure detected (high risk: 0.85). At runtime the required workflow calls UnifAPI GEO endpoints (e.g., geo/mentions/search, geo/serp, geo/mentions/cross-aggregated-metrics) that ingest and return live public AI-search results and citations, which are outsider-authored free text (web/AI answer content) used to compute mention/citation metrics.