frontend-design

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

• Third-party content exposure detected (high risk: 0.90). The skill's design-extraction and ai-multimodal workflows (see design-extraction-overview.md and ai-multimodal-overview) — including explicit integration with chrome-devtools and examples referencing competitor sites and galleries like Dribbble/Awwwards/Mobbin — require the agent to capture and analyze screenshots from public websites or user-provided images, i.e., ingesting untrusted third-party content for runtime analysis.