figma-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's required workflow explicitly calls the Figma MCP server (e.g., create_design_system_rules, get_design_context, get_screenshot, and the assets endpoint) to fetch user-provided Figma content which the agent must read and act on to generate implementation rules and code, exposing it to untrusted, third-party content that could carry indirect prompt injections.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires runtime calls to the Figma MCP server at https://mcp.figma.com/mcp (declared in agents/openai.yaml) to fetch the create_design_system_rules template/prompts that directly drive the agent's instructions, and the MCP connection is listed as a required dependency.