dental-reputation-benchmark

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

• Third-party content exposure detected (high risk: 0.78). The required runtime workflow calls UnifAPI operations (local/search, maps/search, seo/serp) to fetch and ingest public listing records and sampled public review text from third-party businesses on the web, which is outsider-authored free text (review bodies) and thus can be used for indirect prompt injection.