practice-area-rank-audit

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow calls UnifAPI endpoints that fetch and ingest public web SERP/map content (e.g., seo/serp, local/search, maps/search, geo/serp, and competitor “relevant pages”), which necessarily includes outsider-authored free text from third-party websites and listings into the agent’s LLM context for analysis.