Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Nuwa Video Gen - MiniMax女娲视频

v1.1.0

视频生成技能,使用 MiniMax 女娲视频生成 API 创建视频(文生视频/图生视频/首尾帧/主体参考)

0· 342·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for superluanxu/nuwa-video-gen.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Nuwa Video Gen - MiniMax女娲视频" (superluanxu/nuwa-video-gen) from ClawHub.
Skill page: https://clawhub.ai/superluanxu/nuwa-video-gen
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required binaries: python3
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install nuwa-video-gen

ClawHub CLI

Package manager switcher

npx clawhub@latest install nuwa-video-gen
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The code and SKILL.md implement text/image/start-end/subject video generation against https://api.minimaxi.com and require MINIMAX_API_KEY and python3 — this matches the skill's stated purpose. However the registry-level metadata in the provided manifest omitted the required MINIMAX_API_KEY and the _meta.json lists a different ownerId than the registry metadata, which is an incoherence in packaging.
Instruction Scope
Runtime instructions are limited to setting MINIMAX_API_KEY, installing requests, running the included Python script, and uploading/downloading through the MiniMax API — the SKILL.md does not instruct reading unrelated files or exfiltrating other secrets.
Install Mechanism
No install spec; this is an instruction-only skill with one included Python script. The only dependency is the requests Python package (pip install requests), which is proportionate and no arbitrary downloads or archives are used.
Credentials
The script legitimately requires a single MINIMAX_API_KEY to authenticate to the MiniMax API. The inconsistency is that the top-level registry Requirements reported 'no required env vars' / 'primary credential: none' while SKILL.md and the script both require MINIMAX_API_KEY — packaging/metadata mismatch that should be resolved before trusting the skill.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system settings, and has normal agent invocation settings. It does not persist beyond its own files.
What to consider before installing
This skill's code and instructions appear to do what the description says (call MiniMax video APIs and save the returned video), but there are red flags in packaging and provenance. Before installing or giving it an API key: 1) Verify the publisher/owner (source is unknown and _meta.json ownerId differs from the registry ownerId). 2) Confirm the API host (api.minimaxi.com) and that your key scope/limits are appropriate. 3) Run the script in an isolated environment (container or VM) the first time and inspect network traffic if possible. 4) Only provide a dedicated MiniMax API key with minimal scope; do not reuse high-privilege keys. 5) Ensure you have permission to upload/use any person images (subject mode involves faces). If you cannot verify the publisher or metadata, treat this as higher risk and avoid supplying sensitive credentials.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🎬 Clawdis
Binspython3
latestvk97ae914jmq7zykrxm5cjxn9f184jytq
342downloads
0stars
1versions
Updated 2w ago
v1.1.0
MIT-0

Nuwa Video Gen - MiniMax 女娲视频生成

使用 MiniMax 女娲视频生成 API,支持4种生成模式:

  1. 文生视频:根据文本描述生成视频
  2. 图生视频:基于图片 + 文本描述生成视频
  3. 首尾帧:首图 + 尾图 + 文本描述生成视频
  4. 主体参考:人脸照片 + 文本描述,保持人物特征一致

前置要求

  • API Key:从 platform.minimaxi.com 获取
  • 安装依赖:pip3 install requests
  • 设置环境变量:export MINIMAX_API_KEY="your-key"

使用方法

Python 脚本(推荐)

# 文生视频
python3 {baseDir}/scripts/video_gen.py --mode text --prompt "描述文字"

# 图生视频
python3 {baseDir}/scripts/video_gen.py --mode image --prompt "描述文字" --image "图片URL"

# 首尾帧生成
python3 {baseDir}/scripts/video_gen.py --mode start_end --prompt "描述文字" --first "首图URL" --last "尾图URL"

# 主体参考(人脸一致)
python3 {baseDir}/scripts/video_gen.py --mode subject --prompt "描述文字" --subject "人脸图片URL"

参数说明

参数说明必填
--mode模式:text / image / start_end / subject
--prompt视频描述文本
--image图生视频的首帧图片URLimage模式必填
--first首尾帧模式的首帧图片URLstart_end模式必填
--last首尾帧模式的尾帧图片URLstart_end模式必填
--subject主体参考模式的人脸图片URLsubject模式必填
--duration视频时长:6 或 10(秒)否,默认6
--resolution分辨率:720P / 1080P否,默认1080P
--output输出文件名(默认 output.mp4)

模型说明

模式模型说明
text(文生视频)MiniMax-Hailuo-2.3标准文生视频
image(图生视频)MiniMax-Hailuo-2.3以图为首帧生成视频
start_end(首尾帧)MiniMax-Hailuo-02开头结尾两图生成视频
subject(主体参考)S2V-01保持人物特征一致

输出说明

  • 视频文件保存到 --output 指定路径(默认为当前目录的 output.mp4
  • Agent 负责将生成的视频文件发送给用户

注意事项

  • 视频生成是异步过程,需要轮询等待(约10-60秒)
  • 推荐轮询间隔:10秒
  • 图片 URL 需要是公开可访问的链接
  • 主体参考模式涉及人脸图片,请确保已获得图片当事人授权

API 文档

Comments

Loading comments...