ClawHub
Back to skill

Security audit

Music Playlist

Security checks for vulnerabilities and agentic risk

Overview

This music-playlist skill is low risk, though its documentation and helper scripts are rough and may not behave exactly as advertised.

Install only if you are comfortable with a simple local playlist helper that may save entries and command history under its own local data directory. Do not rely on the remove command to erase saved data unless the implementation is fixed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger text is very broad ('music playlist' plus expansive bilingual capability descriptions), which can cause the skill to activate in contexts where the user did not clearly request it. Over-broad activation increases the chance of unintended routing, confused behavior, and misuse of the skill outside its intended scope, especially in systems that auto-select skills from natural-language descriptions.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file branding and help text present this as a playlist/data-management utility with commands such as add, list, remove, and export. However, cmd_remove only echoes a removal message and writes to history.log; it never modifies the underlying data file, directly contradicting the documented intent of a remove operation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
68% confidence
Finding

The skill's natural-language description is predominantly in Chinese and does not indicate that users may choose their preferred language or locale. This can be a language/locale policy concern if the skill defaults to one language without offering an opt-in or alternative.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This shell script writes user-supplied content to the persistent data file using >> "$DB", which affects local user data. Although the command prints a success message after writing, there is no prior warning in comments or help text that add persists input to disk, so the data-modifying behavior is not clearly disclosed to the user.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.