ClawHub
Back to skill

Security audit

GMGN Skill Portfolio

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a coherent GMGN wallet-analysis helper, but its first-time setup handles and persists sensitive credentials in a way users should review before installing.

Install only if you are comfortable using gmgn-cli, creating a GMGN API key, and storing that key locally in ~/.config/gmgn/.env. After setup, remove any leftover /tmp/gmgn_private.pem file and use a GMGN key with the least privileges available. Treat wallet reports as sensitive financial data and avoid sharing raw output publicly.

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
95% confidence
Finding
The skill instructs the agent to inspect local network interfaces and query an external IP-check service to diagnose IPv6 routing. That behavior exceeds the stated purpose of wallet portfolio analysis and unnecessarily expands access to host/network environment details, which could disclose local configuration or normalize unrelated reconnaissance steps.

Context-Inappropriate Capability

High
Confidence
98% confidence
Finding
The first-time setup section directs the agent to generate an Ed25519 keypair and configure credentials locally, which is a privileged action unrelated to merely analyzing wallet data. This creates new secrets and modifies the user's environment, increasing the chance of credential mishandling, persistence of sensitive material, and abuse beyond the skill's declared scope.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs writing an API key into a persistent local file without warning the user that this stores a sensitive credential on disk. Even with restrictive file permissions, silent persistence increases the risk of accidental disclosure, reuse by other processes, and long-lived exposure if the host is shared or backed up.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.