product-design

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and analyzes arbitrary user-provided Figma files (via Figma MCP: http://127.0.0.1:3845/mcp or https://mcp.figma.com/mcp) — including metadata, variables and design context — so the agent ingests untrusted, user-generated third-party content as part of its workflow.