ClawHub
Back to skill

Security audit

VoiceLabs: Reading Text Aloud

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently converts user-provided text into VoiceLabs audio and returns a temporary audio link, with no hidden local code or persistence found.

Install only if you are comfortable sending the text you provide to VoiceLabs for speech generation and receiving a temporary hosted audio link. Avoid submitting confidential text unless your VoiceLabs account and data terms fit that use.

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

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This markdown skill describes generating speech and returning an audioUrl, but the top-level description does not clearly warn users that an external audio link will be produced and handed back. Because this involves transmitting user-provided text to a third-party service and returning hosted output, a brief privacy/data-handling warning would improve user disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.