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 ingests and processes user-created Figma content via the Pixelbyte Figma MCP (e.g., figma_get_file_structure/figma_get_node_details and "Download assets from spec") and reads the generated docs/figma-reports/{file_key}-spec.md (including grep("## Flagged for LLM Review")) as part of its required workflow, so untrusted third‑party design content can materially influence agent routing, model selection, and downstream actions.