← 返回 Skills 市场
6368
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
Before installing, treat cloud transcription as third-party processing of potentially sensitive recordings, keep API tokens out of shell history and source control, and install optional Python/Conda tools in a dedicated virtual environment or container with reviewed package versions where possible.
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
Credentials
The requested environment use is proportionate: local audio files, FFmpeg/ffprobe, optional local transcription tools, and explicit optional API workflows for transcription or diarization.
Install Mechanism
The skill documents common pip and conda install commands for optional transcription tools without version pins or hashes. This is common for instructional skills but users should install in an isolated environment and verify package provenance.
Instruction Scope
The scope says cloud services are not accessed without the user knowing, and the transcription guide labels AssemblyAI and Deepgram as API-based; however, it could more explicitly warn that audio or transcript data may leave the user's environment when API services are used.
Persistence & Privilege
No artifact-backed evidence shows persistence, privilege escalation, background services, memory writes, hidden tool modification, destructive behavior, or automatic execution beyond user-directed commands.
Purpose & Capability
The skill provides Markdown guidance for FFmpeg audio processing, loudness normalization, podcast workflows, and transcription of user-provided audio files; these capabilities match its stated purpose.
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 6368 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