figma-flutter-mcp-design-to-code

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the MCP to fetch and analyze user-provided Figma files/links via the Figma API (see "Getting Figma Links" and "Core Workflows"), which are untrusted, user-generated third-party content that the agent reads and uses to drive code-generation and tool actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running remote code as a required runtime dependency (via npx figma-flutter-mcp and by cloning/executing code from https://github.com/mhmzdev/figma-flutter-mcp.git), which causes fetched external code to be executed and therefore directly controls agent behavior.