vwu.ai OpenAI Models

调用 vwu.ai 平台上的多款 GPT-4 和 GPT-5 系列模型，兼容 OpenAI API，支持标准聊天补全接口。

Security Scan

The skill is internally coherent: it wraps vwu.ai’s OpenAI-compatible API and only needs an API key; the only inconsistency is that the registry metadata did not declare the VWU_API_KEY environment variable that the SKILL.md and script require.

Purpose & Capability

Name/description say this calls vwu.ai OpenAI-compatible models, and the included script and models list do exactly that (POST to vwu.ai/v1/chat/completions). The requested capability (an API key) is appropriate for the stated purpose.

Instruction Scope

SKILL.md gives limited, explicit instructions (set VWU_API_KEY, run vwu-chat with model and prompt). The runtime script only reads models.txt in the same directory and the VWU_* env vars and performs an API call; it does not attempt to read unrelated system files or exfiltrate data to unexpected endpoints.

Install Mechanism

No install spec and only a small shell script are included (instruction-only style). Nothing is downloaded or written to disk by an installer, so install risk is low.

Credentials

The skill requires VWU_API_KEY (and optionally VWU_BASE_URL) to operate — this is proportional to its function. However, the registry metadata lists no required environment variables, which is an inconsistency. Also note the script prints a masked prefix of the API key in error messages (first 8 chars + ***), which may leak part of the key into local logs/console.

Persistence & Privilege

The skill is not flagged always:true, does not request persistent system-wide changes, and does not modify other skills or agent configs. It runs as an invocation-only helper script.

Assessment

This skill appears to do what it says: call vwu.ai models using an API key. Before installing, verify you trust vwu.ai and obtain your API key from their console. Note the registry metadata omits the required VWU_API_KEY — the SKILL.md and script both require it, so you will need to set it yourself. If you are conservative about secrets, inspect the vwu-chat.sh file (it’s small) and be aware it prints a masked prefix of your key to the console on quota errors and allows overriding VWU_BASE_URL via env var (avoid setting VWU_BASE_URL to untrusted addresses). If you want extra caution, run the script in a restricted environment or review network traffic to confirm it only talks to https://vwu.ai.

openai Models for vwu.ai

vwu.ai 平台上的 openai 模型调用技能。

支持的模型

• gpt-4.1
• gpt-4o
• gpt-4o-2024-08-06
• gpt-4o-mini
• gpt-5-mini
• gpt-5.1
• gpt-5.1-chat
• gpt-5.2
• gpt-5.2-chat

共 9 个模型。

配置

使用前需要设置 vwu.ai API key:

export VWU_API_KEY="your-key-here"

获取 key: https://vwu.ai 控制台

使用示例

# 调用模型
vwu-chat --model gpt-4.1 "你的问题"

API 兼容性

所有模型兼容 OpenAI API 格式，支持标准 chat completions 接口。

额度提示

如果使用时提示"额度不足"或类似错误：

1. 访问 https://vwu.ai
2. 在控制台充值或调整额度
3. 或生成新的 API key

---

由 Claw 自动生成 | 源数据: vwu.ai