ClawHub

Xiaomi-any2speech

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaomi text-to-speech and voice-cloning workflow, but users should understand that supplied text, files, URLs, and voice samples may be uploaded to external services.

Install only if you are comfortable sending the selected content and any reference voice recordings to Xiaomi's public API, and generated audio to Feishu if you ask for that feature. Avoid private documents or sensitive voice samples unless you have permission and understand the third-party handling risk.

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 (2)

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill sends user text, URLs, local files, and reference voice recordings to an external Xiaomi API, including sensitive biometric-style voice samples, but does not present a clear privacy notice or explicit consent step at the point of collection. In this context, voice cloning materially increases risk because users may not realize their content and voice data are being transmitted off-device to a third party.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The optional Feishu flow uses tenant tokens or app credentials and uploads generated audio to Feishu, but the skill lacks a strong user-facing warning about credential use and third-party transmission. Even though it says to do this only on explicit request, the absence of a clear consent/privacy notice increases the chance of users exposing content to an external messaging platform without understanding the implications.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal