a1-yandex-kit-launch-check

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow explicitly follows the merchant-provided b2c_url and then reads/fetches storefront pages (including variants, products, categories, discounts, promocodes, gifts, and order history), meaning outsider-authored free text from that public storefront can be ingested without selecting a specific item first.