entity-optimizer

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "Proceed with the audit using public search results, AI query testing, and SERP analysis" and the Data Sources section requires querying public third‑party sources (Google Knowledge Graph API, Wikidata, Wikipedia, social media and industry sites), which the agent would ingest and interpret as part of its workflow.