figma-implement-design

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

• Third-party content exposure detected (high risk: 0.85). The required workflow calls get_design_context and get_screenshot using a user-supplied Figma URL/nodeId, which causes the agent to ingest Figma-authored (outsider) free-form text/metadata from the remote Figma file into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill declares and uses a runtime MCP endpoint (https://mcp.figma.com/mcp) to fetch design payloads via get_design_context/get_screenshot which are injected into the agent's context and drive the agent's implementation instructions, so this external URL is a required runtime dependency that directly controls agent behavior.