d2c-build

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and ingests user-provided Figma designs via the Figma MCP (get_design_context / get_screenshot) and reads layer names, text, and screenshots as required inputs that drive component selection, token mapping, and code-generation decisions, so untrusted third-party content can materially influence the agent's actions.