marimo-notebook

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown documentation and contains no executable scripts or binaries.
  • [COMMAND_EXECUTION]: The instructions guide the agent to use standard development tools such as uv, marimo, and pytest for running, linting, and testing notebooks.
  • [EXTERNAL_DOWNLOADS]: Includes instructions for installing common data science libraries and browser binaries (via Playwright) from official registries and well-known services.
  • [SAFE]: The skill proactively includes security guidance, specifically warning against reading sensitive files like .ssh or .env and recommending the use of --sandbox for execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 04:44 AM