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 instructs the agent to fetch and interpret user-generated design content and assets from the Figma MCP server (e.g., get_design_context, get_screenshot, assets endpoint) and to use that content to drive code-generation and implementation decisions, which could allow untrusted third-party content to influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill calls the Figma MCP server at runtime (e.g., create_design_system_rules / get_design_context / get_screenshot) which returns foundational prompt/templates that directly control agent instructions—see the Figma MCP server documentation: https://developers.figma.com/docs/figma-mcp-server/.