ClawHub
Back to skill

Security audit

CAI: hyperliquid-with-cai

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed CAI/Hyperliquid trading helper with real financial risk but no hidden code, persistence, or unrelated data access in the inspected artifact.

Install only if you intend to let CAI help trade Hyperliquid perpetuals. Use platform scope instead of full scope when possible, understand that deposits and approveAgent authorization can enable live leveraged trading through a custodial workflow, and confirm order details before any live trade.

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
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill operationalizes live perpetuals trading and explicitly references optional deposits, custodial addresses, and hosted approval flows, but it does not include a clear user-facing warning about trading risk, liquidation risk, or the custody/authorization implications of enabling automation. In a trading skill, that omission can cause users to authorize or fund accounts without understanding financial loss exposure or that a custodial workflow and derived agent key are involved.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.