figma-library-builder

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

• Third-party content exposure detected (high risk: 0.70). The required workflow instructs the agent to “Load Figma's current library-generation skill from the official MCP guide distribution” (a public web/GitHub-sourced guide), which can cause the LLM to ingest outsider-authored free text from that distribution at runtime.

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

• Potentially malicious external URL detected (high risk: 0.90). SKILL.md explicitly instructs to "Load Figma's current library-generation skill from the official MCP guide distribution," which points to https://github.com/figma/mcp-server-guide and therefore indicates fetching external repository content at runtime that could control prompts or execute code.