iopho-analyzing-videos

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script uses ffmpeg to extract frames from videos. It implements safe command execution by passing arguments as a list to subprocess.run, which effectively prevents command injection.
  • [EXTERNAL_DOWNLOADS]: The skill requires the google-generativeai package, which is the official and trusted SDK for Google's Gemini models.
  • [DATA_EXFILTRATION]: Video files are uploaded to Google's Gemini File API for processing. This is a core part of the skill's functionality and is directed to a well-known, trusted service.
  • [SAFE]: The dynamic context commands in SKILL.md are used solely for environment validation, such as checking for necessary tools and environment variables, without exposing sensitive data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 04:33 AM