qinghu-ozon-hot-product

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads product rankings, details, and market data from a third-party API endpoint (iqinghu.com) which returns product text (titles, descriptions, trends) authored by various marketplace sellers.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to query a third-party API endpoint (https://www.iqinghu.com/api/desktop/qh/mcp) at runtime to retrieve tool definitions, execute actions, and fetch business data.