med-spa-reputation-benchmark

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

• Third-party content exposure detected (high risk: 0.95). The skill’s required runtime workflow calls UnifAPI operations (local/search, maps/search, seo/serp) to ingest public web listing data including outsider-authored review body text (reviews written by other users) into the agent’s LLM context for analysis (e.g., “Recent review cadence” and “Review language sample”).