Walkie-Talkie Mode

Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to "talk" instead of type.

This skill's behavior is plausible but inconsistent: SKILL.md requires local scripts/binaries (tools/transcribe_voice.sh, bin/sherpa-onnx-tts, ffmpeg, whisper-cpp) that are neither included nor declared. Before installing or enabling it, verify: 1) where those binaries/scripts will come from and that they are from trusted sources; 2) the exact content of tools/transcribe_voice.sh (so it doesn't run unexpected commands); 3) that you are comfortable the agent can execute local binaries on the host. If you can't audit or control the referenced scripts/binaries, consider not installing or asking the author for a clear dependency list and safe installation instructions. Providing the missing files or explicit dependency declarations (and ideally checksums or official sources) would reduce the concern and could change the assessment to benign.

Type: OpenClaw Skill Name: walkie-talkie Version: 1.0.0 The skill bundle describes a 'walkie-talkie' mode for WhatsApp, using local tools for voice transcription and text-to-speech. The `SKILL.md` file outlines a workflow that involves executing local scripts (`tools/transcribe_voice.sh`) and binaries (`bin/sherpa-onnx-tts`) and writing temporary files to `/tmp`. Crucially, the constraints explicitly state 'Use local tools only', which mitigates concerns about remote execution or data exfiltration. There is no evidence of prompt injection, malicious execution, data exfiltration, or other harmful behaviors in the provided content. The described actions are consistent with the stated purpose.