hyperliquid-market-data
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with the Hyperliquid API endpoints (
api.hyperliquid.xyzandapi.hyperliquid-testnet.xyz) to fetch real-time market data. These operations are essential for the skill's function as a market data tool. - [COMMAND_EXECUTION]: Instructions include the use of
curlandjqwithin a bash function to execute POST requests against remote API endpoints and parse the resulting JSON data. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted market data from a public API, creating an attack surface for indirect prompt injection.
- Ingestion points: API responses containing asset metadata, coin names, and market context are fetched and presented to the agent context.
- Boundary markers: The instructions do not define explicit delimiters or headers to isolate external data from internal logic.
- Capability inventory: The skill features network interaction (curl) and local file system access (writing CSV files to a workspace directory).
- Sanitization: Data is processed using structured formats (JSON/CSV) which provides basic structural validation but does not filter content for embedded natural language instructions.
Audit Metadata