figma
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill calls the external Figma MCP server (https://mcp.figma.com/mcp) and uses tools like get_design_context and get_screenshot to ingest and interpret user-provided Figma frames/nodes and assets, meaning the agent will read arbitrary third-party/user-generated content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill declares a required runtime tool endpoint "https://mcp.figma.com/mcp" (the Figma MCP server) which the agent calls (get_design_context, get_screenshot, etc.) and which returns structured design data and generated React/Tailwind code that directly guides the agent's instructions/output, so this external URL can control agent behavior at runtime.
Audit Metadata