ClawHub
Back to skill

Security audit

Crypto Trader

Security checks across malware telemetry and agentic risk

Overview

This crypto-trading skill needs review because it advertises autonomous leveraged futures trading without clear safeguards and delegates behavior to an unbundled local engine.

Only install after reviewing the external engine it calls and confirming it cannot place live trades without your explicit approval. Use paper trading or read-only exchange keys first, avoid broad API permissions, and require hard position, leverage, and drawdown limits before any live use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Missing User Warnings

High
Confidence
96% confidence
Finding
The skill advertises fully autonomous, 24/7 leveraged cryptocurrency trading with unlimited concurrent positions and aggressive strategies such as momentum chasing and pre-pump accumulation, but it provides no warnings about financial loss, liquidation risk, exchange/API abuse, or the need for human oversight. This is dangerous because users may deploy a high-risk trading agent without understanding that 10x leverage and unrestricted autonomous execution can rapidly amplify losses and create severe financial harm.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The description is highly promotional and includes external referral links, but it does not define concrete trigger scope, activation conditions, or operational boundaries for the skill. In an agent ecosystem, vague marketing-style descriptions can mislead users or orchestrators about when the skill should be invoked, increasing the chance of unintended activation for sensitive financial actions and steering users toward third-party services.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal