figma-to-landing-page

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public Figma designs and prototype pages (calls like get_design_context/get_screenshot via the Figma MCP server in Steps 3.2/4.1 and Playwright MCP browser_navigate for prototype URLs in Step 5.1), and the agent is expected to read and interpret that untrusted, user-generated third‑party content to drive component mapping and code generation—so external content can materially influence actions.