Vidu

调用vwu.ai平台上的vidu系列模型，支持7种型号，兼容OpenAI API格式，需配置vwu.ai API密钥使用。

This skill appears to be what it says (a client for vwu.ai Vidu video models) but has metadata inconsistencies you should address before trusting it: 1) The scripts require an API key (VWU_API_KEY) and CLI tools (curl, jq, base64, etc.), yet the registry metadata lists no env vars or binaries — verify these requirements locally. 2) Inspect the scripts before use; they send your API key to VWU_BASE_URL and will follow whatever URL is set there, so do not set VWU_BASE_URL to an untrusted host. 3) Be aware the scripts print the first 8 characters of your key on some errors (logs/terminal), which is minor exposure — avoid pasting real keys into shared logs. 4) Because the package includes executable shell scripts, run them in a controlled environment or review them carefully before executing. If you need higher assurance, ask the publisher to update the registry metadata to declare VWU_API_KEY and required binaries, and to remove or document any behavior that prints secrets or allows endpoint overrides.

Type: OpenClaw Skill Name: vwu-vidu Version: 1.1.0 The skill bundle provides a legitimate interface for interacting with the vwu.ai video generation platform. It contains shell scripts (vwu-chat.sh and vwu-video.sh) that use curl to communicate with the vwu.ai API, and documentation (SKILL.md) explaining how to configure and use the tools. No evidence of data exfiltration, malicious execution, or prompt injection was found; the scripts focus entirely on their stated purpose of video generation and status tracking.