replicate

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses child_process.spawnSync and spawn to execute ffmpeg and ffprobe in scripts/measure.mjs. These are used for video analysis (measuring frame differences, histograms, and audio spectrums). The commands are constructed using static arguments with user-provided file paths, which is necessary for the skill's primary function of video replication.
  • [DATA_EXPOSURE]: The script reads local video files and WebVTT transcripts to perform analysis. It also writes JSON and Markdown reports to a local output folder. This behavior is standard for a video processing workflow and no exfiltration patterns were found.
  • [REMOTE_CODE_EXECUTION]: While the skill uses npx openfilm, these are calls to the platform's primary toolkit (OpenFilm) as specified in the skill's own context and instructions. The scripts included in the skill are localized to the skill folder and do not fetch or execute external code from untrusted remote sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 08:53 PM