ClawHub
Back to skill

Security audit

Ai Cosmology

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed, purpose-aligned ClawHub/OpenClaw helper with no evidence of hidden execution, exfiltration, or destructive behavior.

Install only if you intend to use ClawHub/OpenClaw maintenance guidance. For workflows involving admin tokens, email, moderation, production deploys, or destructive migrations, read the command before running it and require the documented confirmation/signoff steps.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.