ClawHub
Back to skill

Security audit

YouTube Music Cast

Security checks across malware telemetry and agentic risk

Overview

The skill’s sensitive behavior is disclosed and fits its purpose of locally casting YouTube audio through Home Assistant.

Install only if you trust the referenced external scripts. Use a dedicated or least-privilege Home Assistant token if possible, keep ~/.youtube-music-cast/config.sh private, revoke the token if it is exposed, and run the media server only on trusted local networks.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are very broad and map to common user intents like playing music or downloading music. In an agent ecosystem, this can cause the skill to be invoked unexpectedly for generic requests, increasing the chance that users are routed into a workflow that downloads third-party content, starts a local server, or uses Home Assistant credentials without clear user intent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The setup flow asks for a Home Assistant long-lived access token and later stores it in a local config file, but the description around setup does not prominently warn about this sensitive credential handling. Users may provide a powerful token without understanding persistence and local exposure risks, which can lead to Home Assistant compromise if the file is readable by other users or accidentally backed up, logged, or committed.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.