adapt

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

• Third-party content exposure detected (high risk: 0.75). The required workflow instructs the user to provide a live site URL and then perform reconnaissance/extraction by fetching the site’s HTML/API responses (and optionally crawling navigation/sitemaps), so outsider-authored page content (or scraped API/JSON-LD) is likely ingested as readable text into the agent/LLM context via the runtime extraction pipeline’s HTTP/HTML/JSON inputs.