ClawHub
Back to skill

Security audit

ESP32 Voice Assistant for Openclaw

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent ESP32 voice assistant setup, with expected third-party speech services and Docker bridge behavior disclosed enough for its purpose.

Before installing, confirm you are comfortable sending voice input and derived text to the selected STT/TTS provider and your OpenClaw endpoint. Protect the API keys in .env, expose the bridge only on a trusted LAN, and review or pin the GitHub repository before running Docker Compose.

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
94% confidence
Finding
The skill clearly routes spoken audio and derived text to third-party STT/TTS providers and an OpenClaw endpoint, but the user-facing description does not prominently warn that voice data may leave the local device and be processed by external services. This creates a privacy and consent risk: users may unknowingly expose sensitive spoken content, transcripts, or metadata to multiple services, especially in always-available voice-assistant contexts.

Static analysis

No suspicious patterns detected.