figma-design-to-code

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

• Third-party content exposure detected (high risk: 0.85). The required workflow calls get_design_context to pull design context from Figma at runtime, which is outsider-authored free text (designer/third-party content) ingested into the agent’s LLM context via the tool’s returned “reference code, screenshot, and contextual hints.”