Video A'Roll Auto Editor v4.7
PassAudited by ClawScan on May 1, 2026.
Overview
The skill appears purpose-aligned for local video rough cutting, but it runs local FFmpeg/Whisper commands and stores transcript/report files, so users should verify dependencies and choose folders carefully.
This appears safe to review as a local video-editing utility. Before installing, make sure you are comfortable running a Python script from an unknown source, install FFmpeg and openai-whisper from trusted sources, use a dedicated work/output folder, and remember that generated reports may include private transcript content from your videos.
Findings (3)
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.
Running the skill will execute local media-processing and transcription tools, which may use significant CPU/GPU/disk resources and process private video content.
The script invokes local FFmpeg and Whisper commands on user-supplied video/audio paths. This is central to the video-editing purpose and uses argument lists rather than shell strings, but users should understand it runs local tools.
subprocess.run(["ffmpeg", "-y", "-i", video_path, ...]); subprocess.run(["python3", "-m", "whisper", audio_path, ...])
Use trusted FFmpeg and Whisper installations, run the script only on intended media, and prefer a dedicated output/work directory.
Users may install system and Python packages that are outside the registry’s declared requirements.
The documentation asks the user to install external dependencies, while the registry metadata declares no required binaries and no install spec. The setup is user-directed and purpose-aligned, but dependency provenance should be checked.
brew install ffmpeg pip install openai-whisper
Install dependencies from trusted package sources and confirm versions before running the skill.
Private speech from videos may be saved in local Markdown reports or temporary transcript files.
The skill persists derived text summaries/transcripts from videos into reports. This is expected for reporting, but those files may contain private spoken content.
Generate single batch report (with transcript summaries)
Review generated reports before sharing them, and clean the work/output directories if the media contains sensitive content.