Security audit

win-music-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Windows music-control shortcut that runs disclosed media-key commands, with minor clarity and consent caveats.

Install this only if you want an agent to control Windows media playback through nircmd. Use it for explicit play, pause, next, or previous-track requests, and be aware it will send local keyboard shortcuts to the host.

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

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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

Findings (3)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The activation condition '需要播放音乐的时候' is broad and underspecified, which can cause the agent to invoke this skill in loosely related situations without clear user confirmation. Because the skill triggers local OS commands that send media-control keypresses, ambiguous activation increases the chance of unintended command execution on the host.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill instructs execution of local system commands via `cmd` and `nircmd` but does not warn that it will interact with the operating system. This reduces operator awareness and can lead to silent execution of host-level actions; while the current commands are limited to media keypress simulation, they still cross the boundary from informational behavior into local command execution.

Natural-Language Policy Violations

Low

Confidence: 85% confidence
Finding: The natural-language content of the skill is entirely in Chinese, which may force a specific language on users without opt-in or explanation. The file does not state that the skill is intended only for a Chinese-speaking audience or provide an alternative language option.

Static analysis

No suspicious patterns detected.