figma-code-connect

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md Step 2–3, the runtime calls the Figma MCP tools get_code_connect_suggestions and get_context_for_code_connect based on a user-supplied Figma URL (with node-id), and then ingests the returned component property values (e.g., TEXT via instance.getString(...)) into the generated template.