create-design-system-rules

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires calling the Figma MCP server (Step 1 and the "Figma MCP Integration Rules" that mandate get_design_context, get_screenshot, and using the assets endpoint), which ingests user-generated Figma content that the agent reads and uses to drive code-generation and asset/implementation decisions, enabling indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires calling the Figma MCP server at runtime to fetch the "create_design_system_rules" guidance/template (which directly supplies the foundational prompt/instructions the agent must follow) — see the Figma MCP Server docs: https://developers.figma.com/docs/figma-mcp-server/.