adk

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs creating Knowledge Bases that index public websites (e.g., DataSource.Website.fromSitemap / fromWebsite / fromUrls in the "Knowledge Bases" section) and shows using execute({ knowledge: [...] }) so the agent will fetch and read untrusted third-party web content to ground and influence autonomous actions.