ClawHub
Back to skill

Security audit

forgex-skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a high-risk crypto trading guide that asks users to install an external CLI, manage private keys, move funds, and run automated market-making trades.

Review carefully before installing. Verify the npm package and maintainer from an independent source, use only throwaway wallets and tiny test amounts at first, avoid passing passwords or private keys directly on the command line, store backups encrypted, and do not use the volume or price-moving features to misrepresent market activity or violate platform or legal rules.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
93% confidence
Finding
The README instructs users to pass passwords on the command line and import/export private keys and wallet backups, but it does not warn that CLI arguments, shell history, process listings, CSV files, and local exports can expose secrets. In a skill centered on managing blockchain wallets and funds, this omission materially increases the risk of credential theft and irreversible asset loss.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The documentation includes destructive operations such as deleting wallet groups and moving funds without explicit warnings about irreversibility, confirmation expectations, or the risk of sending assets to the wrong address. Given that blockchain transfers and deletions are often irreversible, understated documentation can lead to permanent loss through user error.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.