figma-implement-design

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-supplied Figma content (via get_design_context, get_screenshot, and asset downloads from the Figma MCP server) from Figma URLs/node IDs as required steps (Steps 1–4), so untrusted third‑party/user-generated design data will be read and used to drive implementation decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill declares and uses a required Figma MCP server at https://mcp.figma.com/mcp during runtime to fetch design contexts, screenshots, and assets which are injected into the agent's context and directly drive its instructions and code-generation behavior.