Back to skill

Security audit

Smart Lights

Security checks across malware telemetry and agentic risk

Overview

The skills mostly match their stated ClawHub maintenance purposes, but the bundled autoreview helper defaults to launching a nested Codex review with full filesystem and approval bypass privileges.

Review this package before installing if you plan to use the autoreview skill. Prefer running its helper with `--no-yolo` or setting `AUTOREVIEW_YOLO=0`, and only use moderation or PR publishing commands when you have explicit targets and are comfortable with the remote changes they perform.

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

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.