implement

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs fetching and using external Figma content ("If Figma URL provided" / "Fetch Figma context... mcp__figma__get_design_context" and "Implement from Figma: [URL]"), which is user-generated third-party content the agent reads and uses to drive implementation decisions, so it can enable indirect prompt injection.