Wiz Smart Light Control

Security checks across malware telemetry and agentic risk

Overview

This skill transparently controls local Wiz smart bulbs and does not show hidden data access, persistence, or unrelated behavior.

Install this only if you want the agent to control Wiz bulbs on your local network. Use explicit prompts with the device name and correct bulb IP, consider confirming on/off or disco actions before execution, use a positive limited disco duration, and consider pinning the pywizlight package version in security-sensitive environments.

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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The example prompts are short, generic household phrases like 'Turn off the light' and 'Change the light color to red,' which are plausible in normal conversation and can unintentionally invoke this skill. Because the skill controls a physical device on the local network, accidental triggering can cause unwanted device state changes and create opportunities for prompt/command routing mistakes in larger agent systems.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal