figma-implement-design

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow requires the agent to fetch and interpret user-provided Figma content via the Figma MCP server (e.g., parsing Figma URLs and calling get_design_context/get_screenshot and downloading assets), which are untrusted/third-party user-generated sources that directly influence implementation decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires a runtime connection to the Figma MCP server at https://mcp.figma.com/mcp which the agent calls (get_design_context, get_screenshot, get_metadata, asset downloads) to fetch content that is injected into the agent's prompts/implementation workflow, so this external URL directly controls agent instructions and is a required dependency.