Audio Chat
Security checks across malware telemetry and agentic risk
Overview
The plugin's code, instructions, and requirements align with its stated purpose (auto-sending Telegram voice replies via Microsoft Edge TTS); it stores small local state and invokes edge-tts/ffmpeg but does not request unrelated credentials or system-wide access.
This plugin appears coherent with its stated purpose. Before installing: 1) Understand that any message text you enable for voice will be sent to Microsoft via edge-tts (speech.platform.bing.com) for synthesis — avoid enabling it for sensitive chats. 2) Ensure ffmpeg and a trusted Python environment with edge-tts are installed (the plugin attempts to use a pinned venv under ~/.openclaw/venvs/audio-chat or falls back to python3). 3) Review and control which channels and user IDs can enable audio_chat (set enabledByDefault:false and access.directOnly:true as recommended). 4) Because it runs system commands (python -m edge_tts, ffmpeg), verify those binaries are the expected versions and come from trusted sources. If you need further assurance, review the full index.ts file locally before enabling the plugin.
SkillSpector
SkillSpector findings are pending for this release.
VirusTotal
No VirusTotal findings