ClawHub
Back to skill

Security audit

qwenspeak

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed remote text-to-speech wrapper that sends text and audio over SSH to a user-chosen QwenSpeak server.

Install only if you understand that generated text, YAML job files, and uploaded or downloaded audio pass through the configured SSH server. Use a server you operate or explicitly trust, avoid cloning voices without clear consent, and review the optional root server installer before running it.

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

Medium
Confidence
95% confidence
Finding
This wrapper forwards the invoked command and any piped stdin directly over SSH to a remote host, meaning user prompts, text content, uploaded data, or voice samples may be transmitted off-box without any explicit disclosure or consent mechanism. In a TTS context, that remote transfer is functionally expected, but it still creates a real data-exposure boundary that becomes dangerous if users assume processing is local or if sensitive content is supplied.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.