ClawHub
Back to skill

Security audit

Speechall command-line tool for fast speech-to-text transcription using multiple providers

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward speech-to-text CLI skill with normal privacy considerations because selected media is sent to an external transcription service.

Before installing, confirm you trust the Homebrew tap or GitHub release source. Prefer the environment variable for the API key, avoid putting secrets directly in shell history, and only transcribe recordings you are authorized and comfortable sending to an external service.

SkillSpector

By NVIDIA
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

Medium
Confidence
96% confidence
Finding
The skill instructs users to provide an API key and upload audio/video for transcription through a third-party cloud service, but it does not clearly warn that both the media content and credentials are sent to an external provider. This can lead users to unknowingly transmit sensitive recordings, regulated data, or secrets to a remote service, creating privacy, compliance, and data-handling risks.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.