GMGN Skill Track

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed GMGN crypto-tracking helper, but users should treat its local API key and private-key setup as sensitive.

Install only if you trust gmgn-cli and GMGN's API setup. Use a dedicated GMGN API credential, do not reuse any funded wallet private key, review ~/.config/gmgn/.env permissions, and rotate or delete the credentials when you no longer need the skill.

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 (2)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill is presented as a data-query/tracking capability, but it also instructs the agent to generate an Ed25519 keypair, collect an API key from the user, and persist both credentials locally. That expands the skill from read-only querying into credential provisioning and secret handling, increasing the attack surface and making accidental disclosure or misuse of authentication material more likely.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The setup flow writes both the API key and the private key into a plaintext file under the user's home directory without an explicit warning in that section about the sensitivity of those values. Persisting long-lived credentials on disk in a predictable location increases the chance of accidental exposure through backups, logs, shell history, workspace sharing, or other local compromise.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal