ClawHub
Back to skill

Security audit

Home Assistant Assist

Security checks across malware telemetry and agentic risk

Overview

This skill is transparent about connecting OpenClaw to Home Assistant, but it can give an agent broad control over real home devices without clear safety or credential guardrails.

Install only if you are comfortable letting OpenClaw send commands that may operate real devices in your home. Use a dedicated least-privilege Home Assistant account or token where possible, keep the token out of chats/logs/source control, prefer HTTPS for HASS_SERVER, and require manual confirmation for locks, doors, garage doors, alarms, covers, HVAC, appliances, and other safety-sensitive actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README encourages natural-language control of smart-home devices including locks, garage doors, thermostats, and other physical-world actuators, but it does not warn users that commands may cause real-world security or safety effects. In this skill context, that omission matters because the skill is specifically designed to execute home-control actions through Home Assistant, so users should be alerted to verify intent before issuing or automating sensitive commands.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README instructs users to place a long-lived Home Assistant token in configuration but does not clearly warn that the token is a sensitive credential that grants API control over the home environment. Because this skill directly bridges an agent to Home Assistant, compromise of that token could allow unauthorized device control, data access, or lateral use of the Home Assistant API.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This skill can trigger real-world actions in a user's home, but the description and usage guidance do not warn users that natural-language requests may immediately control physical devices. In a smart-home context, missing safety disclosure increases the risk of unintended activation of locks, appliances, alarms, or other sensitive entities if the user or upstream agent misphrases a request.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The setup instructions require a long-lived Home Assistant access token but provide no warning about secure storage, least privilege, rotation, or the consequences of token leakage. In practice, exposure of this token could grant broad control over the user's Home Assistant instance and connected devices, making credential mishandling a meaningful security risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.