figma-create-design-system-rules

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

• Third-party content exposure detected (medium risk: 0.30). In the required workflow, the agent calls the Figma MCP server tools (e.g., get_design_context/get_metadata/get_screenshot) and then uses the returned Figma node/screenshot text and assets as inputs to generate rules, so outsider-authored content can be ingested via the user’s Figma nodes.