hyperliquid

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified.
  • Ingestion points: Market metadata, order book levels, and user account states are retrieved from the Hyperliquid API (api.hyperliquid.xyz).
  • Boundary markers: The documentation does not specify the use of delimiters or 'ignore embedded instructions' markers for data retrieved from the external API.
  • Capability inventory: The skill can execute high-impact financial actions, including placing, modifying, and cancelling orders, as well as managing account leverage and vault deposits.
  • Sanitization: There are no documented steps for the agent to sanitize or escape data returned from the API before it is processed in a reasoning context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:24 AM