Skip to main content

voiceclaw

Enables local voice input and output for OpenClaw agents, transcribing audio and generating voice replies without network dependency.

Install this skill

or
75/100

Security score

The voiceclaw skill was audited on Feb 28, 2026 and we found 5 security issues across 2 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

medium line 61

Template literal with variable interpolation in command context

SourceSKILL.md
61```bash
medium line 13

Access to hidden dotfiles in home directory

SourceSKILL.md
13{ "name": "WHISPER_MODEL", "description": "Path to ggml-base.en.bin model file (default: ~/.cache/whisper/ggml-base.en.bin)" },
medium line 15

Access to hidden dotfiles in home directory

SourceSKILL.md
15{ "name": "VOICECLAW_VOICES_DIR", "description": "Path to directory containing .onnx voice model files (default: ~/.local/share/piper/voices)" }
medium line 53

Access to hidden dotfiles in home directory

SourceSKILL.md
53| `WHISPER_MODEL` | `~/.cache/whisper/ggml-base.en.bin` | Path to Whisper model file |
medium line 55

Access to hidden dotfiles in home directory

SourceSKILL.md
55| `VOICECLAW_VOICES_DIR` | `~/.local/share/piper/voices` | Directory containing `.onnx` voice model files |
Scanned on Feb 28, 2026
View Security Dashboard
Installation guide →
GitHub Stars 2.2K
Rate this skill
Categorysupport
UpdatedMay 13, 2026
openclaw/skills