ClawHub
Back to skill

Security audit

天谱乐音乐生成大师

Security checks across malware telemetry and agentic risk

Overview

This skill appears to generate music, songs, or lyrics through the Tianpuyue API and save the results locally as advertised.

Install only if you trust Tianpuyue with the prompts, lyrics, and voice-selection details you provide. Use a dedicated OUTPUT_ROOT if you want generated files and logs contained, and avoid putting sensitive content in prompts because prompts and task metadata are written to local logs.

SkillSpector

By NVIDIA
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
90% confidence
Finding
The skill clearly requires environment variables, writes files under OUTPUT_ROOT, and calls an external provider, yet it declares no explicit permissions model beyond metadata requirements. This creates a transparency and policy-enforcement gap: an orchestrator or user may invoke the skill without realizing it can access secrets, perform network requests, and write local files.

Vague Triggers

Medium
Confidence
75% confidence
Finding
The trigger list includes broad, common phrases such as 'BGM', '背景音乐', 'AI 音乐', and '生成音乐', which can cause the skill to activate in loosely related conversations. Mis-triggering is dangerous here because the skill can call an external service and persist outputs locally, so accidental invocation could expose user prompts to a third party or create unwanted files.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
Although the document mentions saving results locally, it does not prominently and explicitly warn users that invoking the skill will write files to the local filesystem under OUTPUT_ROOT. This weak disclosure is risky because users may assume a preview-only or remote-only operation, while the skill actually persists generated content and metadata locally.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.