figma-create-design-system-rules

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (Step 1 and the "Figma MCP Integration Rules") instructs the agent to call the Figma MCP server (create_design_system_rules, get_design_context, get_screenshot) and consume assets from the Figma MCP assets endpoint—user-generated/untrusted Figma content that the agent must read and that directly guides implementation decisions, so it could carry indirect prompt-injection instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill calls the external Figma MCP server at runtime (e.g., create_design_system_rules, get_design_context, get_screenshot) to fetch templates and guidance that directly control agent prompts/instructions—see the Figma MCP Server docs: https://developers.figma.com/docs/figma-mcp-server/.