← Back to Skills Marketplace
Veo Video Generator
by
Kenneth Gerald Hamilton
· GitHub ↗
· v1.2.2
646
Downloads
2
Stars
1
Active Installs
5
Versions
Install in OpenClaw
/install veo-video-generator
Description
Generates high-fidelity 1080p videos with synced audio using Google Veo 3.1. Use for creating cinematic clips from text descriptions.
Usage Guidance
This skill is internally consistent for generating videos via Google's GenAI SDK, but before installing: 1) Confirm you're comfortable providing GEMINI_API_KEY (it will be sent to Google's APIs and may incur billing). 2) Review and trust @google/genai from npm (package-lock uses registry.npmjs.org, which is normal). 3) Note the repository/source and homepage are missing — consider running npm install and the script in an isolated environment (or inspect the installed node modules) before granting keys. 4) The script writes generated .mp4 files into the workspace — ensure storage and privacy policies are acceptable. 5) If you use an alternate Google credential (GOOGLE_API_KEY), be aware the SDK may accept it; provide only the least-privilege key needed. If you want higher assurance, ask the publisher for a repository/homepage and a signed release or run the code in a sandboxed container.
Capability Analysis
Type: OpenClaw Skill
Name: veo-video-generator
Version: 1.2.2
The skill bundle is designed to generate videos using Google Veo. Both the `SKILL.md` instructions and the `generate.js` code demonstrate strong security awareness, explicitly warning against and implementing defenses for shell injection vulnerabilities by requiring argument array invocation and performing input sanitization against shell metacharacters. There is no evidence of data exfiltration, unauthorized execution, persistence, or other malicious behaviors. The dependencies listed in `package.json` and `package-lock.json` are standard for the Google GenAI SDK.
Capability Assessment
Purpose & Capability
Name/description, required binaries (node, npm), dependency (@google/genai) and the single required env var (GEMINI_API_KEY) all match the stated purpose of calling Google's Veo/GenAI video API.
Instruction Scope
SKILL.md instructs npm install and to invoke generate.js with an argv array (execFile-style). The included generate.js only uses process.env for GEMINI_API_KEY, sends the prompt to the Google GenAI SDK, polls for the operation, downloads the generated video to a local .mp4, and does not read arbitrary local files or transmit data to non-Google endpoints. The script also contains a shell-metacharacter rejection guard as defense-in-depth.
Install Mechanism
Installation is via npm (npm install). package-lock.json points to registry.npmjs.org packages (no unusual download URLs or ad-hoc extracts), which is a standard, traceable install mechanism — moderate risk typical of npm packages.
Credentials
Only GEMINI_API_KEY is required (declared as primaryEnv). The SDK notes it may also accept GOOGLE_API_KEY, but no unrelated secrets or extraneous credentials are requested.
Persistence & Privilege
Skill is not forced-always; it is user-invocable and can be invoked autonomously (platform default). It does not request persistent agent-wide privileges or modify other skills/configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install veo-video-generator - After installation, invoke the skill by name or use
/veo-video-generator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.2
- Added package.json to the repository.
- Initial setup for Node.js dependencies and package management.
- Bump glob version to address security risk
v1.2.1
- Improved security instructions: clarified that user prompts must be passed as discrete arguments (not interpolated shell strings) to prevent shell injection.
- Added an explicit code example for secure script invocation.
- Expanded guidance in the Security & Privacy section to emphasize shell injection risks and prevention.
- No changes to functional features or requirements.
v1.1.1
- Updated description and instructions for clarity, specifying default output as 1080p video with audio.
- Added "npm install" setup requirement and included "npm" in required binaries.
- Revised Security & Privacy section for more precise scope and environment details.
- No changes to source code detected; documentation only update.
v1.1.0
- Remove dotenv lib from package.json
- Remove references to local .env in generate.js
v1.0.0
- Initial release of veo-video-generator.
- Generate high-fidelity 4K videos with synchronized audio via Google Veo 3.1 API.
- Supports prompts for audio and video generation from user text.
- Requires GEMINI_API_KEY and Node.js to run.
- Outputs .mp4 files optimized for mobile preview (default 1080p, 9:16).
- Ensures privacy: only text prompts are sent to the API unless reference images are provided.
Metadata
Frequently Asked Questions
What is Veo Video Generator?
Generates high-fidelity 1080p videos with synced audio using Google Veo 3.1. Use for creating cinematic clips from text descriptions. It is an AI Agent Skill for Claude Code / OpenClaw, with 646 downloads so far.
How do I install Veo Video Generator?
Run "/install veo-video-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Veo Video Generator free?
Yes, Veo Video Generator is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Veo Video Generator support?
Veo Video Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Veo Video Generator?
It is built and maintained by Kenneth Gerald Hamilton (@kghamilton89); the current version is v1.2.2.
More Skills