ai-visibility-fix-plan

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 geo/serp, seo/serp, and browser/markdown to fetch and convert live public web pages/serp results into readable text for the agent, which can include outsider-authored free-form content (e.g., third-party pages) that is then placed into the LLM context.