bingx-standard-trade
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external BingX API endpoints. While the current implementation is restricted to read-only operations, the content returned by the API represents an external data source that enters the agent's context.
- Ingestion points: API response data from the
allPosition,allOrders, andbalanceendpoints is returned to the agent inSKILL.mdvia thefetchSignedutility. - Boundary markers: The instructions do not define specific delimiters or boundary markers for the API-sourced content when it is presented to the user.
- Capability inventory: The skill's primary capabilities are limited to authenticated
GETrequests for account and market data. No destructive actions (writes or executions) are enabled within this specific skill. - Sanitization: The skill mandates strict input validation rules (regex patterns and forbidden character checks) for parameters supplied by the user to mitigate injection into the API request structure.
Audit Metadata