ClawHub
Back to skill

Security audit

Home Assistant

Security checks for vulnerabilities and agentic risk

Overview

This Home Assistant skill is broad and powerful, but its capabilities are disclosed, scoped to Home Assistant, and include confirmation requirements for write and destructive actions.

Before installing, understand that this skill can control Home Assistant and may create, replace, or delete automations, scenes, and scripts if you approve those actions. Use it with an account whose Home Assistant permissions match what you want the agent to be able to do.

SkillSpector

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
90% confidence
Finding
The trigger text is intentionally broad: 'Use this skill for ANY Home Assistant request.' That can cause the agent to route all Home Assistant-related tasks through a highly capable connector, including write and destructive operations, even when a narrower or read-only path would be safer. In this context, the risk is unintended invocation and overbroad capability exposure rather than direct code execution.

Static analysis

No suspicious patterns detected.