Wjs Editing Multicam
PassAudited by VirusTotal on May 13, 2026.
Overview
Type: OpenClaw Skill Name: wjs-editing-multicam Version: 0.1.0 The skill bundle provides a legitimate toolset for automated multicam video editing based on audio energy levels. It consists of Python scripts (autoedit.py, render_cuts.py, render_pip.py) that use FFmpeg and NumPy to process local media files and generate an Edit Decision List (EDL). No evidence of data exfiltration, malicious execution, or prompt injection was found; the use of subprocess for FFmpeg is appropriate for the stated purpose.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The skill will invoke ffmpeg on the media files and can overwrite the chosen output file.
The render script runs a local ffmpeg command to process media and write the requested MP4. This is central to the skill's video-editing purpose and uses argument lists rather than shell execution, but it is still local command execution.
cmd = ["ffmpeg", "-nostdin", "-y"] ... subprocess.run(cmd, check=True)
Use it only on media files and output paths you intend to process; confirm the output filename before rendering.
The skill may fail unless ffmpeg and the needed Python packages are already available.
The metadata does not declare runtime requirements, while the included scripts rely on ffmpeg and numpy. This is not suspicious by itself, but it may surprise users or cause setup failures.
Required binaries (all must exist): none ... No install spec — this is an instruction-only skill.
Before use, verify that ffmpeg and numpy are installed in the environment where the skill will run.