ClawHub

AI Mine

Security checks across malware telemetry and agentic risk

Overview

This mining skill is mostly aligned with its stated purpose, but it handles wallet/API secrets and installs live remote code with too little scoping or warning.

Review this before installing. Use only a dedicated low-value wallet, avoid pasting a private key into chat, prefer secure environment injection, limit the OpenAI key, and inspect or pin the AIMineRes/PoAIW code before allowing npm install or starting the miner.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger examples include very generic phrases like "status" and "check balance," which can cause the skill to activate during unrelated conversations and perform actions such as local API calls or mining control unexpectedly. In a skill that installs software and starts or stops a miner, accidental invocation is more dangerous than in a read-only skill because it can change system state and consume resources.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill instructs users to provide a wallet private key and OpenAI API key via environment or chat without a prominent warning about the sensitivity of those secrets or the risks of sharing them in conversation. Because a blockchain private key grants direct control over wallet assets, mishandling it can lead to irreversible financial loss, and the skill context makes this particularly dangerous.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal