keyword-research

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

• Third-party content exposure detected (high risk: 0.85). The skill calls UnifAPI operations like seo/competitors/ranked-keywords, seo/competitors/domain-intersection, and especially seo/serp at runtime; those operations ingest and summarize outsider-authored public web SERP content (e.g., third-party pages/domains) into the LLM context as evidence for winnability.