vwu.ai kling Models

Access and use seven kling language models on vwu.ai platform with OpenAI-compatible chat completions via API key authentication.

Security Scan

The skill largely does what it says (calls vwu.ai models) but registry metadata omits required environment variables and binaries and the included script exposes a configurable base URL and partial API-key output — these inconsistencies could be accidental but warrant caution before installing.

Purpose & Capability

The skill's code and SKILL.md match the stated purpose: calling vwu.ai's OpenAI-compatible chat endpoint for the listed kling models. However the registry metadata does not declare the VWU_API_KEY credential (required by the script) nor the dependency on common CLI tools (curl, jq, zsh). That mismatch is unexpected.

Instruction Scope

SKILL.md and the script stick to the advertised task: sending a chat completion request to vwu.ai and printing the response. They do not read unrelated user files or system state beyond environment variables and the shipped models.txt.

Install Mechanism

There is no install spec (instruction-only), which is low-risk. The skill includes a shell script that runs in-place; it relies on curl and jq but these are not declared in metadata—users should ensure those binaries are present from trusted sources.

Credentials

The script requires VWU_API_KEY but the registry lists no required env vars or primary credential. The script also accepts VWU_BASE_URL (default https://vwu.ai) though SKILL.md does not document this override; that means the request target (and thus where an API key might be sent) can be redirected via an env var. Additionally, on API errors the script prints the first 8 characters of the key, which leaks part of the secret.

Persistence & Privilege

The skill does not request persistent or elevated platform privileges (always:false). It does not modify other skills or system-wide settings.

What to consider before installing

This skill appears to implement the claimed vwu.ai model calls, but there are a few red flags you should address before using it with real credentials: (1) The registry metadata does not declare the required VWU_API_KEY or the needed CLI tools (curl, jq, zsh) — assume you must provide these. (2) The script allows VWU_BASE_URL to be overridden by an environment variable but SKILL.md doesn't mention that; consider hardcoding or verifying VWU_BASE_URL is set to https://vwu.ai to avoid accidentally sending your key to another endpoint. (3) The script reveals the first 8 characters of your API key in error messages; avoid using your main/long-lived key—use an ephemeral or limited-scope key if possible. (4) Review the vwu-chat.sh file yourself (or run it in an isolated environment) before exporting any secrets. If you plan to install broadly, ask the author to update registry metadata to declare VWU_API_KEY and required binaries and to document/lock the base URL.

kling Models for vwu.ai

vwu.ai 平台上的 kling 模型调用技能。

支持的模型

• kling-v1
• kling-v2-1
• kling-v2-1.master
• kling-v2-5-turbo
• kling-v2-6
• kling-v2.master
• kling-v3

共 7 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 kling-v1 "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