figma-to-code

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and fetches external Figma content (e.g., user-provided figma.com URLs or desktop selections) via MCP tools—calling get_design_context, get_metadata, get_variable_defs, screenshots and asset URLs as part of its required operating procedure—so untrusted, user-created Figma layer text, comments, URLs, or generated code can be read and influence implementation and mapping decisions.