neighborhood-guide-opportunity

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls UnifAPI endpoints like seo/serp, seo/competitors/relevant-pages, geo/serp, news/search, maps/search, and local/search, which fetch/ingest live public web content and SERP/AI-citation text from third-party sites into the agent’s LLM context (outsider-authored free text via public web/marketplace pages and search results).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires connecting to the UnifAPI MCP endpoint (https://mcp.unifapi.com) at runtime to fetch live seo/geo/maps/news data which is injected into the agent's context and directly controls its prompts/evidence, making this a required external runtime dependency.