ClawHub
Back to skill

Security audit

LIFX

Security checks across malware telemetry and agentic risk

Overview

The skill is for controlling LIFX lights, but it may run some state-changing light actions without confirmation because not all write actions are labeled correctly.

Review this skill before installing if you want strict confirmation for every change to your lights. The connector use and credential handling are disclosed, but `toggle_power` and `turn_effects_off` should be treated as write actions even though the skill does not tag them that way.

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 phrase 'Use this skill for ANY LIFX request' creates an overly broad routing rule that can cause an agent to invoke this skill without sufficient task-level constraints or safety checks. In context, the skill exposes both read and write operations against a real LIFX account, so broad auto-selection increases the chance of unintended state-changing actions being routed here and executed with connected credentials.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.