figma-implement-design

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md instructs loading “Figma's current implementation skill from the official MCP guide distribution” (a runtime fetch of external guide content), which can introduce outsider-authored free text into the agent’s LLM context via the MCP guide distribution/integration layer.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to "Load Figma's current implementation skill" from https://github.com/figma/mcp-server-guide, which means it would fetch external instructions that directly control the agent's behavior.