figma-flutter-mcp-design-to-code

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

• Third-party content exposure detected (low risk: 0.10). The agent reads design data and text from selected Figma links provided by the user, which constitutes low-risk outsider-authored content access.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs cloning and installing an external MCP server repository from GitHub (https://github.com/mhmzdev/figma-flutter-mcp.git), which constitutes an unofficial operational remote dependency evaluated as medium tier.