Voice TTS/ASR

语音输入（Whisper ASR）+ 语音输出（Edge TTS）技能，支持 agent 专属音色，可调用 send_voice_reply.mjs 发送 Telegram 语音消息。

Before installing: 1) Verify the package includes the Python wrapper scripts referenced at scripts/whisper and scripts/edge_tts — they are referenced but not present in the provided files; without them ASR/TTS calls will fail. 2) Be aware install.sh will pip install edge-tts/whisper and download a large Whisper model (~hundreds of MB) from the network — plan disk space and network usage. 3) The skill reads ~/.openclaw/openclaw.json to obtain Telegram bot tokens; ensure that file is trustworthy and that you are comfortable the skill can access your bot tokens (or prefer to pass --token to send_voice_reply.mjs). 4) Note config parsing uses vm.runInNewContext rather than JSON.parse — this will execute the contents as JS in a VM; only use if you trust your openclaw.json. 5) If you proceed, test in a sandboxed environment first (no sensitive tokens) and confirm TTS/ASR work and that the missing Python wrappers are present/functional. If the wrappers are missing, request the complete package from the author or decline installation.

Type: OpenClaw Skill Name: voice-tts Version: 2.0.1 The skill exhibits several high-risk patterns and vulnerabilities. Most notably, 'lib/config.mjs' and 'scripts/send_voice_reply.mjs' use 'vm.runInNewContext' to parse the main OpenClaw configuration file (~/.openclaw/openclaw.json), which constitutes a potential Remote Code Execution (RCE) vulnerability if the configuration file is tampered with. Additionally, 'bin/voice-asr.mjs' employs a prompt-injection technique by appending mandatory 'system-level' instructions to transcribed text to force the agent into using specific tools, which could be abused to hijack agent behavior. Finally, core logic files referenced in the code ('scripts/whisper' and 'scripts/edge_tts') are missing from the provided bundle, preventing a full security audit of the actual ASR/TTS execution.