ClawHub
Back to skill

Security audit

推荐音乐（recommend-music）

Security checks across malware telemetry and agentic risk

Overview

This skill only provides music recommendations and does not request system access, credentials, installs, or background execution.

Safe to install for Chinese-language song recommendation use. Expect possible over-activation on broad music questions, and verify song metadata separately if accuracy matters because the skill relies on the model's knowledge rather than a live music database.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger conditions are broad enough to match common conversational requests like asking for music or background audio, which can cause the skill to activate in situations where the user did not explicitly intend to invoke this specialized workflow. Over-broad activation can misroute user requests, override more appropriate skills, and reduce user control, especially in multi-skill agent environments.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The skill is written entirely in Chinese and instructs output in Chinese without any mechanism to detect or respect the user's preferred language. In a multilingual system, this can cause usability failures, misunderstandings, and unintended disclosure or miscommunication if the user cannot read the response language.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.