web-design-expert

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly ingests external, user-provided and public content — e.g., the Figma MCP workflow that extracts colors/typography/images from user-shared Figma file URLs and the mcp__magic__21st_magic_component_inspiration / logo_search tools that search external UI patterns and logos — so the agent will read and interpret arbitrary third‑party/user‑generated content as part of its workflow.