1k-perps-module

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle user prompts and codebase files related to financial trading. While this presents a surface for indirect injection, the skill includes explicit instructions to avoid bypassing security filters, signing requirements, and risk validation.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to use Bash for legitimate development operations, such as running yarn jest for unit testing and verifying SDK versions via node. These commands are standard for the described development workflow.
  • [EXTERNAL_DOWNLOADS]: The skill references official documentation at hyperliquid.gitbook.io, which is a well-known service in the DeFi ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 08:38 PM
Security Audit — agent-trust-hub — 1k-perps-module