huolala-figma-mcp

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls the MCP tool figma_to_code_package with a user-supplied figma_url, and the service fetches that Figma design content (public web content / third-party authored text) and then ingests it into the generated ZIP as readable index.html and dsl.json that the agent uses as LLM context—so outsider free text can flow into the LLM via the fetched design.