← 返回 Skills 市场
5971
总下载
2
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install audio
功能描述
Process, enhance, and convert audio files with noise removal, normalization, format conversion, transcription, and podcast workflows.
安全使用建议
Install this if you want an audio workflow helper. Work in a dedicated folder, keep backups of source recordings, review generated file lists before using concat commands, and avoid sending sensitive recordings to cloud transcription services unless you have approval and understand the provider's privacy and retention terms. Use environment variables for real API tokens instead of pasting secrets into commands or shared files.
功能分析
Type: OpenClaw Skill
Name: audio
Version: 1.0.1
The skill bundle is classified as suspicious due to significant shell injection vulnerabilities. Specifically, the use of `ffmpeg -f concat -safe 0` in `commands.md` and `podcast.md` allows arbitrary file paths in the concatenation list, posing a risk if the agent constructs this list from unsanitized user input. Additionally, other shell commands involving command substitution and arithmetic (`$()`, `bc`) in `commands.md` and `podcast.md` could lead to arbitrary code execution if user-provided input is not properly sanitized by the OpenClaw agent before being passed to the shell.
能力评估
Purpose & Capability
The skill's capabilities match its stated purpose: converting, cleaning, normalizing, transcribing, and preparing audio files using documented audio tools.
Instruction Scope
The instructions are scoped to user-provided audio files and user-requested commands; optional API transcription is visible, though the privacy implications could be clearer.
Install Mechanism
There is no executable installer or payload, but optional transcription tools are installed through ordinary pip or conda examples without pinning.
Credentials
Local shell commands, FFmpeg processing, batch conversion, and output file creation are proportionate for audio work; users should still review filenames and paths before running batch or concat examples.
Persistence & Privilege
No persistence, background execution, privilege escalation, or credential harvesting is declared; API keys and Hugging Face tokens appear only as placeholders for optional external transcription workflows.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install audio - 安装完成后，直接呼叫该 Skill 的名称或使用
/audio触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
Declare required binaries (ffmpeg, ffprobe), add requirements section with optional deps, add explicit scope
v1.0.0
Initial release
元数据
常见问题
Audio 是什么？
Process, enhance, and convert audio files with noise removal, normalization, format conversion, transcription, and podcast workflows. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 5971 次。
如何安装 Audio？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install audio」即可一键安装，无需额外配置。
Audio 是免费的吗？
是的，Audio 完全免费（开源免费），可自由下载、安装和使用。
Audio 支持哪些平台？
Audio 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（linux, darwin, win32）。
谁开发了 Audio？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.1。
推荐 Skills