# Detect prohibited items by description

Judges: One listing. Questions: choice:policy - \[policy menu,allowed\]. Action: Auto-remove high-confidence; queue unsure.

Grade: C — A clean typed decision with low volume or low value, or too vague to act on.. Score: 5.09.

Vertical: E-commerce & retail.

Function: E-commerce ops.

Status: Idea.

Volume: routine.

Value: major.

Risk: high.

Evidence: null.

Flags: human-review.

- [Vertical](/verticals/ecommerce_retail/)
- [Function](/functions/ecommerce/)
- [Nyckel content moderation classifier](/use-cases/nyckel-content-moderation-classifier/)
- [E-commerce search query intent classification](/use-cases/e-commerce-search-query-intent-classification/)
- [Detect restricted or regulated product in seller upload](/use-cases/detect-restricted-or-regulated-product-in-seller-upload/)
- [Detect off-platform payment solicitation in messages](/use-cases/detect-off-platform-payment-solicitation-in-messages/)
- [Detect counterfeit-risk language in listings](/use-cases/detect-counterfeit-risk-language-in-listings/)
- [Detect when a seller is circumventing fees through coded language](/use-cases/detect-when-a-seller-is-circumventing-fees-through-coded-language/)