ClawHub
Back to skill

Security audit

Currents API

Security checks across malware telemetry and agentic risk

Overview

The package is purpose-built for ClawHub maintenance, but it includes high-impact moderation commands and a review helper that runs nested Codex with full access by default.

Install only in a ClawHub maintainer or trusted development environment. Use `--no-yolo` or `AUTOREVIEW_YOLO=0` for autoreview unless full local access is intentional, and run moderation commands only after checking the exact target, reason, credentials, and audit expectations.

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.