ClawHub
Back to skill

Security audit

mlx-whisper

Security checks for vulnerabilities and agentic risk

Overview

This skill gives straightforward local speech-to-text command examples and does not show hidden, unrelated, or high-impact behavior.

Install only if you want local MLX Whisper transcription. Treat generated transcripts and subtitles as potentially sensitive files: choose output folders deliberately, manage file permissions, and delete outputs or cached models when no longer needed.

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

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The examples instruct the user to write transcription and subtitle outputs to local disk using -o ./output and -o ./subs, but the documentation does not explicitly warn that potentially sensitive audio content will be persisted as plaintext transcript or subtitle files. In a speech-to-text skill, this omission can lead to unintentional storage of sensitive data on disk, especially when users assume processing is ephemeral because it is local and does not use an API key.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.