vipshop-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill package explicitly calls public vip.com APIs (e.g., https://mapi-pc.vip.com/... and https://mapi-file-tx.vip.com/... as shown in vipshop-img-product/scripts/img_search.py and vipshop-product-detail/scripts/detail.py and documented in multiple SKILL.md files) to ingest product data, images and user-generated content (reviews) which the AI is required to parse/display and use to drive follow-up actions (search, detail lookup, paging, link generation), creating a clear avenue for indirect prompt injection from untrusted third‑party content.