ClawHub
Back to skill

Security audit

Qwen3-TTS + Feishu Voice

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it advertises, but its Feishu sending script has unsafe filename handling that could run local code if used with a crafted audio filename.

Review before installing. Use a virtual environment, protect FEISHU_APP_SECRET, only send audio that is appropriate for Feishu and the chosen recipient, and avoid running scripts/send_voice_feishu.sh on filenames from untrusted sources until the filename handling is fixed.

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
87% confidence
Finding
The skill instructs users to upload generated audio and use Feishu credentials to authenticate against external APIs, but it does not clearly warn that voice content and metadata will leave the local machine and be transmitted to a third party. In a skill marketed as 'fully local' TTS, that omission can mislead users about privacy boundaries and cause unintended disclosure of sensitive spoken content.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.