← 返回 Skills 市场
Openai Whisper Api
作者
Peter Steinberger
· GitHub ↗
· v1.0.0
26005
总下载
52
收藏
1180
当前安装
1
版本数
在 OpenClaw 中安装
/install openai-whisper-api
功能描述
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
安全使用建议
Install only if you are comfortable sending the selected audio file to OpenAI for transcription and using your OPENAI_API_KEY. Choose the --out path deliberately, because the script will overwrite a writable file at that location.
功能分析
Type: OpenClaw Skill
Name: openai-whisper-api
Version: 1.0.0
The skill is classified as suspicious due to a local file write vulnerability in `scripts/transcribe.sh`. The `--out` parameter allows the user to specify an arbitrary file path for the transcription output, which could lead to overwriting sensitive files (e.g., configuration files, startup scripts) if the user has write permissions to those locations. While the skill's primary purpose is legitimate, this lack of output path validation presents a significant security risk, potentially enabling data corruption or persistence if exploited by a malicious actor.
能力评估
Purpose & Capability
The stated purpose is to transcribe audio via OpenAI's transcription API, and the script does only that: validates an input file, requires OPENAI_API_KEY, calls the OpenAI audio transcription endpoint with curl, and writes the response.
Instruction Scope
The instructions are narrow and user-directed, though users should understand that audio contents are sent to an external API and that --out controls the local destination file.
Install Mechanism
The package contains SKILL.md and one shell script, with metadata requiring curl and OPENAI_API_KEY; there are no install hooks, package downloads, background services, or automatic startup changes.
Credentials
Network access and an OpenAI API key are proportionate for API-based transcription. The output path is user-specified and can overwrite files the user can write, which is common for CLI tools but worth using carefully.
Persistence & Privilege
No artifact-backed evidence of persistence, privilege escalation, credential harvesting, hidden file indexing, or background execution was found.
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 openai-whisper-api - 安装完成后，直接呼叫该 Skill 的名称或使用
/openai-whisper-api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
v1.0.0
元数据
常见问题
Openai Whisper Api 是什么？
Transcribe audio via OpenAI Audio Transcriptions API (Whisper). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 26005 次。
如何安装 Openai Whisper Api？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openai-whisper-api」即可一键安装，无需额外配置。
Openai Whisper Api 是免费的吗？
是的，Openai Whisper Api 完全免费（开源免费），可自由下载、安装和使用。
Openai Whisper Api 支持哪些平台？
Openai Whisper Api 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Openai Whisper Api？
由 Peter Steinberger（@steipete）开发并维护，当前版本 v1.0.0。
推荐 Skills