ClawHub
Back to skill

Security audit

iaiops-building

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed building-automation integration that can read facility systems and includes gated control actions, so it should only be installed by authorized operators.

Install this only in environments where the user is authorized to access building systems. Keep write and publish tools in dry-run/MOC mode, confirm approvals outside the agent when changing setpoints or outputs, and avoid loading it for casual HVAC questions if no facility-system access is intended.

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
83% confidence
Finding
The activation text uses a very broad set of trigger terms for common building and HVAC concepts, which can cause the skill to activate for loosely related requests. In this skill, over-activation is more dangerous than normal because the toolset includes high-impact building control functions, including MOC-gated write/command operations against BACnet, BAS, and MQTT targets.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.