ClawHub

Clawhub

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed ClawHub skill manager that can install or update persistent skills, with normal supply-chain risk but no evidence of hidden or malicious behavior.

Install only if you trust ClawHub and the npm `clawhub` CLI. Confirm any global CLI installation yourself, review third-party skills before enabling them, and be careful with `update --all` because installed skills persist and can affect future OpenClaw sessions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The WhatsApp flow says the agent will handle CLI installation, which implies a remote conversational channel could trigger package installation and system modification without a clear confirmation step. That is dangerous because it lowers the barrier to unreviewed code installation and may cause unintended changes on the host from a casual message.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal