frontend-design

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and analyzes user-provided screenshots and external design references (see "MANDATORY workflow for screenshot/image/design inputs" and references/design-extraction-overview.md which names competitor websites and galleries like Dribbble/Awwwards/Mobbin), so the agent is expected to read and interpret untrusted public third‑party content as part of its workflow.