ClawHub
Back to skill

Security audit

🏡 Home Assistant Builder (hab)

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Home Assistant CLI helper, with expected but powerful access that users should handle carefully.

Install this only if you trust the upstream Home Assistant Builder GitHub releases and are comfortable giving the CLI a Home Assistant token. Prefer least-privileged tokens, use read-only or dry-run/plan commands first, and approve deletes, restarts, backup restore/delete, network changes, and ESPHome hardware actions only after reviewing the exact command.

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
80% confidence
Finding
The trigger description is very broad, covering nearly any Home Assistant terminal operation, dashboard edit, backup, ESPHome action, or mention of `hab`. Overly broad invocation increases the likelihood the skill is auto-selected in contexts involving sensitive or destructive operations, causing shell-backed commands to be suggested or run when a narrower, safer skill or additional review would be more appropriate.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.