← 返回 Skills 市场
Openai
作者
aiwithabidi
· GitHub ↗
· v1.0.0
910
总下载
0
收藏
8
当前安装
1
版本数
在 OpenClaw 中安装
/install openai
功能描述
OpenAI API integration — chat completions, embeddings, image generation, audio transcription, file management, fine-tuning, and assistants via the OpenAI RES...
安全使用建议
This skill claims to be a full OpenAI CLI and only asks for your OPENAI_API_KEY, which is reasonable in principle — but the implementation has inconsistencies that raise caution. Before installing or running it: 1) Inspect the script yourself (or ask someone you trust) — it looks like a lightweight wrapper but uses nonstandard API paths and methods and will likely not perform some operations (file uploads, transcriptions) as advertised. 2) Note it will try to read WORKSPACE or ~/.openclaw/workspace/.env to find OPENAI_API_KEY if the environment variable is absent; make sure that file doesn't contain other secrets you don't want read. 3) If you test it, use a limited-scope or expendable API key and small test inputs. 4) Verify the skill's provenance (homepage and author links) and prefer an implementation that uses the official OpenAI endpoints/SDK or clearly documents a proxy. 5) If you need the declared features (multipart uploads, audio file uploads, generation flows), demand a corrected implementation that actually sends files and proper request bodies. If you are not comfortable auditing the code, treat this as untrusted and avoid installing it with a production or high-privilege API key.
功能分析
Type: OpenClaw Skill
Name: openai
Version: 1.0.0
The skill bundle is a non-functional facade that claims to provide comprehensive OpenAI API integration but contains logic that is entirely disconnected from the actual OpenAI API. Specifically, `scripts/openai.py` uses incorrect HTTP methods (GET instead of POST for chat/embeddings), targets non-existent endpoints (e.g., `/v1/chat`), and completely ignores user-provided arguments like chat prompts or file paths in its command functions. Furthermore, `SKILL.md` claims support for non-existent models like 'GPT-5'. While no direct evidence of data exfiltration to third-party domains was found (it hardcodes `api.openai.com`), the deceptive nature of the implementation combined with its access to sensitive `OPENAI_API_KEY` credentials from environment variables and local `.env` files makes it highly suspicious.
能力评估
Purpose & Capability
Name/description claim full OpenAI REST coverage (chat, embeddings, images, transcribe, TTS, file upload, fine-tuning, assistants). The script only issues simple GET/POST calls to nonstandard paths (e.g., /chat, /embed, /file/upload) rather than the canonical OpenAI endpoints and methods; many features (e.g., file upload, transcription, image generation) appear declared but not properly implemented (no multipart upload, no request bodies for many operations). This mismatch suggests the code is a stub or expects a proxy rather than the real OpenAI REST API.
Instruction Scope
SKILL.md claims all requests go directly to OpenAI and that nothing is stored locally, but the script will attempt to read a .env file at WORKSPACE (or ~/.openclaw/workspace/.env) to extract OPENAI_API_KEY if the env var is not set. The manifest declared no required config paths but the code does access user files. The instructions also encourage commands (file-upload, transcribe, tts) that the CLI does not implement correctly (it never reads files from disk to send them), so running those commands will not perform the expected actions.
Install Mechanism
No install spec; the skill is instruction-only with an included Python script (stdlib-only). Nothing is downloaded or written during an install step, which is low risk.
Credentials
Only OPENAI_API_KEY is declared and used as the primary credential, which is appropriate for an OpenAI integration. However, the script also reads the WORKSPACE env var and a .env file at ~/.openclaw/workspace/.env (if present) to find the key. That file lookup is not declared in the metadata and could read configuration files in the user's home directory; while it only parses the OPENAI_API_KEY line, reading user config files is broader access than advertised.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide configuration, and does not persist data. Autonomous invocation is permitted (platform default) but not combined here with other high privileges.
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 - 安装完成后，直接呼叫该 Skill 的名称或使用
/openai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
- Initial release of the OpenAI API integration skill for Python (stdlib only, zero dependencies)
- Supports chat completions (GPT-4o, GPT-5, o1), embeddings, DALL-E image generation, Whisper audio transcription, text-to-speech, file management, fine-tuning, assistants, moderation, and model listing
- Includes a CLI interface with commands for each OpenAI API operation (chat, embed, image, transcribe, tts, files, fine-tune, moderate, usage, assistants, and more)
- Outputs JSON by default; use --human for readable output
- Requires only the OPENAI_API_KEY environment variable—no data stored locally
元数据
常见问题
Openai 是什么？
OpenAI API integration — chat completions, embeddings, image generation, audio transcription, file management, fine-tuning, and assistants via the OpenAI RES... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 910 次。
如何安装 Openai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openai」即可一键安装，无需额外配置。
Openai 是免费的吗？
是的，Openai 完全免费（开源免费），可自由下载、安装和使用。
Openai 支持哪些平台？
Openai 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？
由 aiwithabidi（@aiwithabidi）开发并维护，当前版本 v1.0.0。
推荐 Skills