figma-implement-design

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

• Third-party content exposure detected (high risk: 1.00). This skill requires fetching and ingesting user-provided Figma content via Figma URLs and the Figma MCP server (get_design_context, get_screenshot, and assets endpoints), which are untrusted, user-generated third‑party sources that the agent reads and uses to drive code-generation and implementation decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires a user-provided Figma URL (e.g., https://figma.com/design/:fileKey/:fileName?node-id=1-2) which is fetched at runtime via get_design_context/get_screenshot and whose returned design context and assets are injected into the agent's context to drive implementation, so external content directly controls prompts.