hyperliquid-market-data

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches market data from official Hyperliquid API endpoints (api.hyperliquid.xyz and api.hyperliquid-testnet.xyz). It also utilizes the hyperliquid Python SDK for data retrieval.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes financial market data from an external API to generate analysis and summaries. \n
  • Ingestion points: Market data is ingested from the Hyperliquid API through curl commands and the Python SDK (SKILL.md). \n
  • Boundary markers: Not explicitly present; the skill relies on the structured nature of the JSON response from the API. \n
  • Capability inventory: Includes network access to official API endpoints and file system write access to the /workspace/trading-desk/data/ directory for saving CSV datasets. \n
  • Sanitization: The data is parsed as structured JSON using jq and the official SDK, which effectively handles the data as typed values rather than raw text instructions.
  • [COMMAND_EXECUTION]: The skill defines and uses shell commands employing curl and jq to interact with the API. These commands are static and do not execute dynamic or user-controlled input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 09:33 AM
Security Audit — agent-trust-hub — hyperliquid-market-data