Openai Whisper 1.0.0
PassAudited by ClawScan on May 1, 2026.
Overview
This is a simple, coherent Whisper CLI transcription skill, with only expected local command use and package/model downloads to consider.
This appears safe for its stated purpose. Before installing, confirm you trust the Homebrew `openai-whisper` package and remember that transcribing sensitive audio creates local output files and downloads Whisper models into the local cache.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing or first running the skill may download software and model files onto the local machine.
The skill depends on an external Homebrew package and a first-run model download. That is expected for a local Whisper CLI skill, but it is still a supply-chain and local storage point users should notice.
metadata: {"clawdbot":{"requires":{"bins":["whisper"]},"install":[{"id":"brew","kind":"brew","formula":"openai-whisper","bins":["whisper"]}]}} ... Models download to `~/.cache/whisper` on first run.Install from trusted Homebrew sources, keep the package updated, and be aware that Whisper model files will be stored locally in the cache.
The agent may run the local `whisper` command on audio files you provide and write transcript files where requested.
The skill instructs use of a local CLI command. This is central to the stated purpose and the examples are scoped to user-provided audio files, so it is a notice rather than a concern.
Use `whisper` to transcribe audio locally. Quick start - `whisper /path/audio.mp3 --model medium --output_format txt --output_dir .`
Use clear file paths and output directories, and review commands before allowing transcription of sensitive audio.