figma-code-connect

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests user-provided Figma files via the MCP tools in SKILL.md (Step 2 and Step 3: calling get_code_connect_suggestions and get_context_for_code_connect with a Figma URL/fileKey/nodeId), so it reads untrusted, user-generated third‑party content and uses that data to drive mapping, template generation, and subsequent actions.