video-comparer

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill documentation describes the use of FFmpeg and FFprobe for video processing. It explicitly mentions avoiding shell=True for subprocess calls to mitigate command injection risks.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill generates reports that load a UI component (img-comparison-slider) from a CDN. This is a standard practice for interactive web reports and does not execute on the agent itself.
  • [NO_CODE] (SAFE): The primary logic file scripts/compare.py was not included in the provided file list. Analysis is based on the README, SKILL.md, and reference documentation which describe the script's intended behavior.
  • [DATA_EXFILTRATION] (SAFE): No indicators of data exfiltration or unauthorized network communication were found. The tool is designed for local file processing.
  • [PROMPT_INJECTION] (SAFE): No prompt injection or instructions to bypass safety filters were detected in the skill metadata or documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 05:28 AM