@tank/figma-to-code

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests Figma MCP outputs (e.g., get_design_context, get_variable_defs, get_metadata, and get_screenshot) derived from a user-supplied Figma URL/node, which is effectively outsider-authored content (public/third-party design file text/metadata) that can be turned into LLM-readable prose/code context.