ClawHub
Back to skill

Security audit

Lyrion Music

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward local music-server control skill with expected network commands and no hidden persistence or unrelated data access.

Install this only if you intend the agent to control an LMS instance on your network. Set LYRION_HOST and LYRION_PORT explicitly, use it on a trusted network, and remember that playback, volume, power, playlist add, and playlist clear commands make real changes to your music system.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill documentation directs the agent to invoke a local shell script, which gives the skill shell-execution capability without any declared permissions. Even though the documented purpose is benign device control, undeclared shell access expands the trust boundary and can be abused if user-controlled parameters are passed through unsafely or if the script behavior changes over time.

External Transmission

Medium
Category
Data Exfiltration
Content
local json="{\"id\":1,\"method\":\"slim.request\",\"params\":[\"$player_id\",[$params]]}"
    
    curl -s -X POST \
        -H "Content-Type: application/json" \
        -d "$json" \
        "$URL"
Confidence
72% confidence
Finding
curl -s -X POST \ -H "Content-Type: application/json" \ -d

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.