ClawHub
Back to skill

Security audit

HyperGrok Desk Risk Limits

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed trading risk-management guide that reads account and market state, writes desk risk records, and restricts rather than expands trade authority.

Install only if you want an agent to help manage Hyperliquid desk risk workflows. It may read live account state and write desk records, and any actual trade-increasing action still requires explicit approval; review the configured limits carefully before relying on PASS/REJECT outputs.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description says to use the skill for "answering "how's the book"", which is a natural-language phrase broad enough to overlap with ordinary conversation about status or performance. The file does not provide explicit trigger boundaries or negative examples to distinguish when this skill should activate versus other desk or analytics skills.

Content

No source excerpt is available for this finding.