Itsyhome Control

• Outcome: Review
• Latest audit: May 28, 2026 at 6:28 AM UTC
• Version:
  1.0.1

Overview

This smart-home skill is transparent and local, but it can operate locks, garage doors, scenes, and sensitive home-state feeds without documented confirmation safeguards.

Install only if you want OpenClaw to control your smart home through Itsyhome. Require explicit confirmation before unlocking doors, opening garages, running security-sensitive scenes, or using debug/camera/live event endpoints, and keep the Itsyhome webhook limited to a trusted local environment.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The manifest description explicitly says to trigger on any smart-home control intent, which is overly broad for a capability that can operate safety-sensitive devices like locks and garage doors. Broad activation increases the chance the agent invokes this skill on vague or unintended requests, leading to unauthorized or unintended physical-world actions.

Missing User Warnings

High

• Confidence: 96% confidence
• Finding: The skill enables control of locks, garage doors, blinds, and other physical devices but provides no warning or safeguard language for safety-critical actions. In this context, omission of warnings and confirmation requirements is dangerous because accidental activation or ambiguous interpretation could unlock doors or open garages, creating immediate physical security risk.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The document exposes direct actuation endpoints for locks, garage doors, blinds, power, thermostats, and scenes without any warning that these actions have physical-world consequences or should require confirmation for sensitive operations. In this skill context, the API is specifically meant to let an agent control a real smart home, so omission of safety guidance materially increases the chance of unsafe or unauthorized actions.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The SSE endpoint is documented as streaming live characteristic updates but provides no privacy warning that these events can reveal occupancy patterns, room presence, lock state, camera-related metadata, and other sensitive household behavior. Because this skill is for smart-home querying and control, real-time telemetry is especially sensitive and could be misused by local malware or over-privileged agents.

VirusTotal

65/65 vendors flagged this skill as clean.