ClawHub
Back to skill

Security audit

音乐

Security checks across malware telemetry and agentic risk

Overview

This music-generation skill is not clearly malicious, but it asks for broad command and file authority that is not well scoped to its stated purpose.

Review this skill before installing. It does not show evidence of exfiltration or destructive behavior, but its shell execution and file access permissions are broader than the documented music-generation workflow. Prefer a version that removes exec or documents exact allowed commands, inputs, outputs, and API endpoints.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The skill declares generic `exec` capability alongside `read` and `write` even though the stated purpose is music generation. That creates an unnecessary execution surface where an agent may run arbitrary shell commands during normal use, enabling command injection, file tampering, or data exfiltration if later prompts or wrappers pass untrusted input into execution paths.

Intent-Code Divergence

Medium
Confidence
91% confidence
Finding
The document claims only allowlisted commands should be executed, but the metadata exposes unrestricted generic `exec`, which defeats that guidance in practice. This mismatch can mislead users and reviewers into believing the skill is constrained when the agent actually has broad command-execution power.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The invocation/use description says the skill should be used for broadly unrelated tasks such as video processing, audio editing, media conversion, and dubbing, despite being presented as a music-generation skill. Overbroad triggering increases the chance an agent invokes this skill in inappropriate contexts, expanding exposure to its powerful tools and encouraging unsafe task-routing.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.