Back to skill
Skillv1.0.0
ClawScan security
视频提取 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 12, 2026, 10:13 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill does what it claims — it wraps ffmpeg to extract frames and has no unrelated requirements, credentials, or network behaviors.
- Guidance
- This skill is a thin wrapper around ffmpeg and appears coherent. Before installing, ensure you: (1) install ffmpeg from a trusted package source (brew in the spec) appropriate for your OS; (2) run the script only on video files you trust (it will create/overwrite the specified output path); and (3) be aware brew may not be available on all platforms (Windows). No credentials or network access are requested by the skill.
Review Dimensions
- Purpose & Capability
- okName/description match the implementation: the skill requires the ffmpeg binary, provides a script that extracts frames, and offers a brew install for ffmpeg. All required components are proportional to the stated purpose.
- Instruction Scope
- okSKILL.md instructs running the included scripts/frame.sh with a video path and output path. The script only checks the input file, creates the output directory, calls ffmpeg to extract a frame, and prints the output path — it does not read other files, environment variables, or contact external endpoints.
- Install Mechanism
- okInstall spec uses the well-known 'ffmpeg' brew formula to provide the required binary. No downloads from arbitrary URLs or extract-from-remote archives are present.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths. The script only uses command-line arguments provided at runtime.
- Persistence & Privilege
- okalways is false and the skill does not request elevated or persistent system privileges. It writes only the output file path provided by the caller and does not modify other skills or global agent settings.