figma-code-connect

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

• Third-party content exposure detected (high risk: 0.75). High likelihood: at runtime the workflow calls the Figma MCP tools (get_code_connect_suggestions / get_context_for_code_connect) using a user-supplied Figma URL, and the returned component property definitions (including TEXT/SLOT content) are then used to generate template code—those tool responses originate from an external Figma document authored by others and can include free text that may be injected into the agent’s LLM context.