ClawHub
Back to skill

Security audit

Transcribing Audio

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently uses VoiceLabs to transcribe audio, save captures, and retrieve prior captures, with no evidence of hidden or destructive behavior.

Before installing, understand that audio sent through this skill is processed by VoiceLabs and saved as a capture in your VoiceLabs account, along with transcript data that can be retrieved later. Avoid using it for sensitive recordings unless that storage and OAuth access are acceptable to you.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description presents transcription as a simple speech-to-text action but does not upfront disclose that the audio and transcript will be saved as a persistent capture in the user's VoiceLabs account. This can mislead users about data retention and storage, causing them to share sensitive recordings under incomplete consent, especially because audio transcripts often contain private or regulated information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.