figma-to-angular

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls get_design_context on the Figma MCP server to fetch Figma designs (reference code, screenshots, and metadata) from public Figma URLs, and instructs the agent to read and act on that untrusted, user-provided content to drive design-to-code decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches Figma designs at runtime (via URLs like https://www.figma.com/design/rKUVGKb7Kw3d6YGoQl6Ho7/Flowbite-Component-Mapping?node-id=33308-25180&m=dev) using get_design_context and uses the returned code, screenshots, and metadata to drive generation and instructions, so the external content directly controls the agent's behavior.