qa

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

• Third-party content exposure detected (high risk: 0.75). High risk: the required runtime workflow fetches live public site content (e.g., sitemap.xml, HTML, and .plain.html from the --base host) and then injects derived free-text like titles/descriptions, excerpts, JSON-LD snippets, and scrape node text into generated report.json/report.html (later consumed into LLM context if the agent summarizes the report).