design-md

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to download and parse HTML and screenshots from screen object fields (e.g., htmlCode.downloadUrl and screenshot.downloadUrl) using web_fetch/read_url_content, which are arbitrary external/user-provided URLs and therefore untrusted third‑party content that the agent will read and interpret.