ClawHub
Back to skill

Security audit

HyperGrok Desk Risk Limits

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent trading-desk risk workflow that reads account state and writes desk records, with no executable code or hidden install behavior.

Install only if you want an agent to use live Hyperliquid account data to make risk decisions and maintain persistent trading-desk records. Review generated risk-limit files and saved book checks because they may contain sensitive account, position, and operational data.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill instructs the agent to write `/workspace/trading-desk/risk-limits.md` after an interview, but it does not require an explicit user-facing confirmation immediately before modifying workspace state. In agent environments, silent file creation or overwrite can cause unintended state changes, audit confusion, or be abused through prompt-driven invocation to persist unauthorized operational settings.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill tells the agent to save a written book check under `/workspace/trading-desk/briefs/YYYY-MM-DD-book.md` when requested, but it omits a clear warning that this creates persistent files in the workspace. While lower risk than changing limits, it still introduces unannounced state changes and possible information retention of sensitive account and position data.

Static analysis

No suspicious patterns detected.