ClawHub
Back to skill

Security audit

ESP32 Voice Assistant for Openclaw

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent ESP32 voice-assistant setup that clearly depends on user-provided voice providers, Docker, LAN device access, and OpenClaw chat integration.

Install only if you are comfortable routing spoken requests through the configured STT/TTS providers and OpenClaw endpoint. Review the provider privacy and retention policies, keep API keys in the local .env file, restrict the bridge to your trusted LAN, and check out/metrics.jsonl if you want to understand what local usage data is retained.

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
95% confidence
Finding
The skill explicitly routes speech audio and conversation content to external providers (xAI and/or ElevenLabs) and also documents local per-turn logging to disk, but it does not present a clear privacy warning in the user-facing description. This creates a real privacy and consent risk because users may unknowingly send sensitive voice data off-device and retain metadata locally without informed consent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.