ClawHub
Back to skill

Security audit

VoiceLabs: Managing Voice Library

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed VoiceLabs voice-library helper with consent checks for voice cloning and no hidden execution or persistence beyond requested voice profiles.

Before installing, understand that cloning a voice sends a short recording or audio URL to VoiceLabs and creates a reusable voice profile in that account. Only use cloning for your own voice or a speaker who has clearly consented; preset voice additions are lower risk and can be created idempotently by name.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description includes the generic trigger "create a custom voice" and the broad catch-all "wants to manage their voice library." These activation cues are not tightly bounded and may overlap with ordinary requests, making it unclear when this skill should activate versus other voice- or media-related skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.