ui-ux-concept-implementation

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow instructs the agent to “collect the target concept, current rendered UI… before editing” from user-provided concepts/screenshots/reference sites and then uses Playwright/DevTools MCP for browser verification, so outsider-authored free text (the user’s concept/request) is ingested without an initial selection gate.