qinghu-ozon-shop-intercept
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the vendor's API (iqinghu.com), including shop rankings, product details, and market trends. If these external sources contain malicious instructions, the agent might inadvertently execute them while summarizing or analyzing the data.
- Ingestion points: External data is ingested via HTTP requests to
https://www.iqinghu.com/api/desktop/qh/mcpand related workflow endpoints inSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to treat the content of the API responses as data rather than instructions.
- Capability inventory: The skill uses network operations (
curl,fetch,requests) and interacts with other skills likeqinghu-excel-exportfor data delivery. - Sanitization: There is no mention of sanitizing or validating the content of the API responses before the agent incorporates them into its analysis or output.
Audit Metadata