← Back to Skills Marketplace
steipete

Video Frames

by Peter Steinberger · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
58261
Downloads
133
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install video-frames
Description
Extract frames or short clips from videos using ffmpeg.
Usage Guidance
Install only if you are comfortable running FFmpeg on local video files. Prefer --time or use simple numeric --index values, and do not pass --index from untrusted or automatically generated input until the script validates it as a non-negative integer.
Capability Analysis
Type: OpenClaw Skill Name: video-frames Version: 1.0.0 The skill bundle is benign. The `SKILL.md` provides clear instructions for extracting video frames using `ffmpeg` and does not contain any prompt injection attempts against the AI agent. The `scripts/frame.sh` script correctly parses arguments, validates input, and executes `ffmpeg` commands with proper quoting, preventing shell injection. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or other high-risk behaviors. The functionality is clearly aligned with its stated purpose.
Capability Assessment
ℹ Credentials
Local file reads and writes are proportionate for video-frame extraction. The FFmpeg filtergraph injection warning is a bounded robustness issue, not evidence of credential access, privilege escalation, exfiltration, or destructive behavior.
✓ Install Mechanism
Install metadata only declares ffmpeg as a required binary and offers a Homebrew ffmpeg install; no hidden installer, remote code retrieval, or package persistence was found.
ℹ Instruction Scope
Runtime instructions are narrow and user-directed, but the optional --index value is passed into an FFmpeg filter expression without numeric validation.
✓ Persistence & Privilege
No cross-session hooks, services, scheduled tasks, memory writes, tool hijacking, or privilege-escalation behavior were present in the inspected artifact files.
✓ Purpose & Capability
The skill purpose is coherent: SKILL.md describes extracting frames or thumbnails from videos, and scripts/frame.sh only invokes ffmpeg to create a requested output image from a local video file.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install video-frames
  3. After installation, invoke the skill by name or use /video-frames
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Metadata
Slug video-frames
Version 1.0.0
License —
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Video Frames?

Extract frames or short clips from videos using ffmpeg. It is an AI Agent Skill for Claude Code / OpenClaw, with 58261 downloads so far.

How do I install Video Frames?

Run "/install video-frames" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Video Frames free?

Yes, Video Frames is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Video Frames support?

Video Frames is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Video Frames?

It is built and maintained by Peter Steinberger (@steipete); the current version is v1.0.0.

💬 Comments