qinghu-ozon-bluesea-hunter
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the
www.iqinghu.comAPI to perform market analysis. This creates a potential surface where adversarial content in the API response could influence the agent's behavior. - Ingestion points: Data is retrieved from
https://www.iqinghu.com/api/desktop/qh/mcpandhttps://www.iqinghu.com/api/desktop/qh/workflow/page. - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to disregard potential instructions embedded within the JSON market data.
- Capability inventory: The agent can execute further network requests based on the analysis and trigger external skills for file exports (e.g.,
qinghu-excel-export). - Sanitization: There is no evidence of sanitization or filtering of the text content received from the third-party API before it is processed by the LLM.
Audit Metadata