ClawHub
Back to skill

Security audit

音乐

Security checks across malware telemetry and agentic risk

Overview

The skill presents as music generation but requests broad read, write, and command execution capabilities without clear music-specific limits.

Review this skill before installing. It may be usable for music prompt generation, but only enable it in an environment where read, write, and shell execution are acceptable, or require the publisher to remove exec/write and document exact allowed operations.

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 (4)

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The skill description claims that risky code and external dependencies were removed, yet the manifest still exposes the exec capability. This mismatch can mislead reviewers and users into granting a broader trust level than warranted, increasing the chance that command execution is available in contexts where it is not expected.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
A music-generation skill should not normally require arbitrary system command execution, so declaring exec materially expands the attack surface. If the skill is invoked in a permissive agent environment, an attacker could potentially steer it into running shell commands unrelated to music generation, leading to local file access, secret exposure, or host compromise.

Description-Behavior Mismatch

Medium
Confidence
90% confidence
Finding
The documented feature set extends from music generation into generic file handling, API integration, and command execution, which is disproportionate to the stated purpose. This broad scope makes prompt abuse and capability confusion more likely, because users may activate a seemingly creative skill that can also manipulate files and invoke external systems.

Vague Triggers

Medium
Confidence
81% confidence
Finding
Ambiguous invocation guidance and missing activation boundaries make it unclear when the skill should engage or what inputs are in-scope. In an agent system with powerful tools, this can cause overbroad triggering or unintended handling of unrelated user requests, increasing the chance that risky capabilities like exec are exposed inappropriately.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.