tables-data-specialist

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is to use a provided “## Web Scan Context” block (which includes a page URL and audit settings) and then perform a web scan; this implies runtime fetching/reading of outsider-authored web page content, which would be ingested as free text into the LLM context for analysis.