ClawHub
Back to skill

Security audit

Xiao Chuang You Music

Security checks for vulnerabilities and agentic risk

Overview

This is a benign music recommendation skill focused on Chinese-style playlists, instruments, and tea-music pairings.

Installers should expect this skill to answer a wide range of music and playlist prompts, including some generic music requests. That may be useful for a music assistant, but narrowing triggers would reduce accidental activation. No high-impact permissions or hidden behaviors were found.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
95% confidence
Finding
The activation terms are broad, generic, and include common phrases such as music, playlist, background music, and recommendation-style prompts. This can cause the skill to trigger on ordinary user requests that may have been intended for a more general assistant flow, leading to unintended routing, reduced predictability, and possible interference with other skills.

Static analysis

No suspicious patterns detected.