frontend-design

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

• Third-party content exposure detected (high risk: 1.00). The skill's mandatory screenshot/design workflow (SKILL.md) and referenced design-extraction and ai-multimodal docs (references/design-extraction-overview.md, references/ai-multimodal-overview.md) require capturing and analyzing public inspiration/competitor websites and galleries (e.g., via chrome-devtools and Dribbble/Awwwards examples), which are untrusted third‑party assets that the agent must read and whose extracted guidelines directly drive implementation decisions.