ClawHub
Back to skill

Security audit

LiveAvatar

Security checks across malware telemetry and agentic risk

Overview

LiveAvatar is a coherent, user-started voice/video avatar skill, with normal privacy considerations because spoken input is transcribed and sent through LiveAvatar and the local OpenClaw agent flow.

Install only if you trust LiveAvatar and the openclaw-liveavatar npm package. Treat spoken input like sensitive conversation data because it may be transcribed and processed by LiveAvatar and then sent to your OpenClaw agent; avoid speaking secrets unless you accept that data flow.

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
93% confidence
Finding
The skill explicitly captures microphone audio, sends speech for transcription via LiveAvatar, and forwards transcribed content to the OpenClaw agent, but it does not present a clear privacy warning before use. This can mislead users about where sensitive voice data goes and increases the risk of accidental disclosure of personal, confidential, or regulated information to third-party services.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.