ClawHub
Back to skill

Security audit

Qq Music Control

Security checks for vulnerabilities and agentic risk

Overview

This skill locally controls QQ Music on macOS, and its side effects are visible, limited, and aligned with that purpose.

Install this only if you want an agent to control your local macOS QQ Music app. It can start QQ Music, bring it to the foreground, skip tracks, toggle playback, and change media volume, so consider narrowing triggers or asking for confirmation before disruptive commands.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation indicates shell execution of a local Python script, but the manifest does not declare corresponding permissions. This creates a transparency and policy gap: users or the platform may not realize the skill can execute code, which increases risk if the script is modified or abused later. In context, the stated functionality does require code execution, so this looks more like an undeclared-capability issue than overtly malicious behavior.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list includes broad, everyday phrases such as '下一首', '音量', 'play music', and 'shuffle', which can be spoken in many normal contexts and may unintentionally activate the skill. Because the skill can execute commands that affect a local application and system media state, accidental invocation can cause unwanted playback, volume changes, or app launches without clear user intent.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The documentation examples rely on ambiguous natural-language commands without clear invocation boundaries, reinforcing a design that may map ordinary conversation directly to executable actions. In a voice- or text-triggered assistant environment, this increases the chance of accidental command execution, especially for media controls that can launch apps or alter playback state immediately.

Static analysis

No suspicious patterns detected.