hyperliquid-setup
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the
hyperliquid-python-sdkfrom PyPI and the@nktkas/hyperliquidandviempackages from the NPM registry. These are standard, well-known libraries required for the skill's primary function of interacting with the Hyperliquid exchange. - [COMMAND_EXECUTION]: Executes shell commands to install dependencies, verify runtime versions for Python and Node.js, and create workspace directories. These operations are standard for a development environment setup.
- [DATA_EXFILTRATION]: The skill performs connectivity checks and readiness verification by sending requests to official Hyperliquid domains (
api.hyperliquid.xyzandapi.hyperliquid-testnet.xyz). These operations are required for the service to function and do not involve sensitive data exfiltration to unauthorized parties. - [INDIRECT_PROMPT_INJECTION]: The skill ingests network configuration and account addresses from a local workspace file (
/workspace/trading-desk/desk.md). This ingestion surface is documented and used solely for configuring read-only API calls and status checks, representing a minimal risk to the agent's logic flow.
Audit Metadata