browse

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates to arbitrary public URLs and ingests page content via Browser actions (e.g., Browser { action: "navigate", url: "..." }, get_state, extract, and evaluate) returning page text and DOM that the agent must read and act on, so untrusted third‑party web content can influence decisions and enable indirect prompt injection.