Maylo Voice Assistant

Offline-first voice assistant stack for macOS (Wake word + VAD recording + local Whisper ASR + OpenClaw agent response + offline TTS via macOS say). Use to i...

What to check before installing: - Expect to install Python packages and possibly download pretrained models; the 'offline-first' claim is accurate at runtime but not during setup — model and pip downloads may occur. Plan for network access during install. - The code invokes the 'openclaw' CLI locally (bridge/milo_responder_openclaw.py). Ensure you intentionally install and trust the openclaw binary on the same machine; the skill will run 'openclaw agent --local' via subprocess. - This is macOS-focused: it calls the 'say' command and uses macOS audio behavior. It will generate a self-signed cert and default to binding the web UI to 0.0.0.0:8443 (accessible on your LAN). If you do not want LAN access, run the web UI on localhost or use a firewall. - The package metadata omits required binaries (openclaw, openssl/uvicorn/runtime expectations). Treat that as a transparency issue: verify prerequisites before running. - If privacy is a concern: inspect recordings/ directory (logs and possible saved WAVs), and consider running the project in an isolated environment (VM or sandbox) and reviewing the bridge/responder logs to confirm all processing is local. - If you want higher confidence: review/verify openclaw installation/source, audit the exact versions of pip packages installed, and search for any unexpected outbound network connections during install and first run.

Type: OpenClaw Skill Name: maylo-voice-assistant Version: 0.1.0 The skill is classified as suspicious due to a significant prompt injection vulnerability. User-transcribed speech is directly passed as the `--message` argument to a local OpenClaw agent instance (`openclaw agent --local --message <text>`) by `assets/app/bridge/milo_responder_openclaw.py`, with the input originating from `assets/app/maylo_assistant/core.py`. This allows user input to potentially manipulate the local AI agent's behavior. Additionally, the skill executes various system commands like `brew install switchaudio-osx` in `scripts/install.sh`, `openssl req` in `scripts/run_web_https.sh`, and `say` in `assets/app/maylo_assistant/core.py`, which, while plausibly for functionality, represent broad system access. No evidence of intentional data exfiltration, backdoor installation, or other malicious activities was found.