ClawHub
Back to skill

Security audit

GMGN Skill Token

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent for GMGN API-based crypto wallet analysis, but users should be aware it stores a GMGN API key locally and includes conditional network troubleshooting.

Install this only if you intend to use GMGN through gmgn-cli and are comfortable storing a GMGN API key in ~/.config/gmgn/.env. Treat the API key as a secret, avoid sharing raw wallet/account outputs publicly, and run the IPv6 troubleshooting steps only when you are debugging the documented 401/403 connectivity issue.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill directs the agent to enumerate local network interfaces and contact an external IP-check service to diagnose IPv6 issues. Those actions exceed the stated token-research purpose and expose host/network metadata, creating unnecessary local reconnaissance and outbound connectivity that could leak environment details or normalize unrelated system inspection.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The first-time setup flow instructs the agent to generate an Ed25519 keypair and write an API key into a persistent file under the user's home directory. Even though setup is operationally useful, it crosses into credential handling and local state mutation, which can create secret-management and persistence risks if done automatically or without strong consent and disclosure.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill tells the agent to write a user-provided API key to ~/.config/gmgn/.env without an explicit warning that the credential will be stored persistently on disk. This increases the chance of users disclosing secrets without informed consent and leaves a plaintext secret available to later processes, tools, or accidental exposure.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.