binance-spot-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a curated OpenAPI schema from the author's official GitHub repository (holon-run/uxc). This schema is used by the uxc CLI tool to map and execute Binance Spot REST operations.
- [COMMAND_EXECUTION]: The skill extensively uses the uxc command-line utility to perform network requests, manage credentials, and execute API operations. It provides clear instructions for setting up CLI bindings and environment variables to safely handle API keys and private signing keys.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Binance API endpoints, creating a potential surface for indirect prompt injection if an attacker were to influence API responses.
- Ingestion points: The skill ingests data from Binance Spot REST API responses (api.binance.com and testnet.binance.vision) during market reads and account/order queries.
- Boundary markers: The instructions specifically advise the agent to use JSON output envelopes and parse stable fields (ok, kind, protocol, data, error) rather than raw text to maintain structure.
- Capability inventory: The skill possesses capabilities for account information retrieval and order placement/cancellation using signed requests.
- Sanitization: The skill relies on the agent's internal JSON parsing and tool-handling logic; it specifically implements guardrails requiring human confirmation for high-risk mainnet write operations.
Audit Metadata