ClawHub
Back to skill

Security audit

Music Generation

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its music-generation purpose, with expected sharing of prompts and lyrics with CellCog and installation of external software.

Send only prompts and lyrics you are comfortable sharing with CellCog, and protect your API key. Review the required base skill and package versions before installing, understand the background completion notifier, and check service costs and usage terms. The full submitted artifact was inspected; external dependency implementations were not audited.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

Using CellCog is consistent with the description, but the supplied code submits only a generic placeholder task. It contains no music-generation request, audio output handling, or implementation of the stated duration and vocal/instrumental features. The visible behavior is generic agent chat, not the advertised music-generation functionality. No additional resource access or unrelated triggers are shown.

Content

No source excerpt is available for this finding.

The workflow sends user prompts and potentially supplied lyrics to CellCog without an explicit privacy disclosure.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The skill instructs the agent to submit the user's task through CellCog's API and also encourages providing specific lyrics at L156. Although CellCog is identified as the provider, the skill never explicitly warns that prompts and supplied lyrics are transmitted to a third-party service, which matters for confidential or unpublished material.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The setup command invokes an unpinned npm package through npx and installs skill content from an unpinned repository reference. A compromised or malicious future release could execute code with the installing user's privileges or introduce adversarial agent instructions; however, the static finding incorrectly describes this as an MCP server reference.

Content

No source excerpt is available for this finding.