No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by HITsz-TMG · Codex Skill · ★ 1.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is VideoClaw safe to install? View the security audit →
Featured in: AI Video Generation & Editing: Seedance, Kling & Subtitles
VideoClaw: AI 创意视频生成员工 简体中文 | English 直接与 OpenClaw 对话："生成 X 的视频" → 搞定。 📺 [
| Stars | 1,789 |
| Forks | 265 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 51.2610279673781/100 |
| Open Issues | 13 |
| Last Updated | 2026-08-26 |
| Created | 2024-08-29 |
| Platforms | python |
| Est. Tokens | ~19k |
These tools work well together with VideoClaw for enhanced workflows:
Looking for a VideoClaw alternative? If you're comparing VideoClaw with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
全网最全的、持续更新的、最火爆的 100+ 人格 蒸馏skills 合集｜ 多agent系统 ｜名人/导演/天涯大神/古籍/二次元/职场/情感全品类
terminally online
Build autonomous AI agents in Python.
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
Agent Skills 终极指南：快速入门、资源推荐、精选技能与实用工具 ｜The Ultimate Guide to Agent Skills: QuickStart, Resources, Features&Too
An Agentic Framework for Reflective PowerPoint Generation
Explore other popular codex skill tools:
VideoClaw is 🚀 AI 全自动化视频生成员工 | Your First AIGC Coworker. Chat an Idea. Get a Film. 🦞. It is categorized as a Codex Skill with 1.8k GitHub stars.
VideoClaw is primarily written in Python. It covers topics such as agent, aigc, filmmaking.
You can find installation instructions and usage details in the VideoClaw GitHub repository at github.com/HITsz-TMG/VideoClaw. The project has 1.8k stars and 265 forks, indicating an active community.
VideoClaw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to VideoClaw on Agent Skills Hub include awesome-ai-persona-skills, milady, Upsonic. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: