Audio Note Taker
PassAudited by VirusTotal on May 11, 2026.
Overview
Type: OpenClaw Skill Name: audio-note-taker Version: 1.0.1 The audio-note-taker skill is a legitimate tool designed to transcribe audio files using the OpenAI Whisper API. The code in source/audio_note_taker.py and the install.sh script perform standard operations consistent with the stated purpose, such as checking for dependencies (openai, ffmpeg), verifying environment variables (OPENAI_API_KEY), and processing local audio files to generate Markdown notes.
Findings (0)
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.
Your OpenAI account credentials are used for transcription requests.
The skill uses the user's OpenAI API key to access OpenAI services. This is expected for the stated transcription purpose, but it uses the user's provider account and may incur usage costs.
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))Use a dedicated or least-privileged OpenAI project key if available, store it securely, and monitor usage charges.
Audio content you process with this skill leaves your machine and is sent to the configured OpenAI-compatible provider.
The selected local audio file is uploaded to the OpenAI transcription API. This is disclosed and purpose-aligned, but audio recordings can contain sensitive conversations.
with open(audio_path, "rb") as audio_file:
transcript = client.audio.transcriptions.create(
model=model,
file=audio_file,Only process recordings you are comfortable sending to that provider, and review the provider/privacy settings before using sensitive meeting, interview, or personal audio.
A future package version could behave differently from the version the author tested.
The install helper pulls the OpenAI package without pinning an exact version. This is a normal dependency for the skill, but open-ended dependency resolution can change behavior over time.
pip3 install --user openai>=1.0.0
In sensitive environments, pin and review dependency versions before installing.
Users may expect summarized decisions, action items, or speaker separation that the current code does not actually produce.
The implementation indicates the smart summary path is not enabled, despite the skill description advertising intelligent summaries and action item extraction.
notes.append("*（需配置 GPT 模型，当前版本暂未启用）*")Verify the generated notes manually and do not rely on advertised summary or speaker features unless the implementation is updated.