frontend-design

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and analyzes user- or web-sourced images/screenshots from public sites (see design-extraction-overview.md and ai-multimodal-overview.md, plus chrome-devtools capture and references to Dribbble/Awwwards/competitor sites), so the agent will read and interpret untrusted third‑party content as part of its workflow.