cursor-talk-to-figma-mcp

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

• Third-party content exposure detected (low risk: 0.10). The skill reads Figma design documents, layers, text content, and annotations via MCP tools, which can contain outsider-authored text injected into design files.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references external runtime installation scripts from bun.sh (https://bun.sh/install and bun.sh/install.ps1) to install the Bun runtime during setup, which constitute third-party/unofficial runtime dependencies.