jupyter-notebook

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script new_notebook.py located at $CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py to scaffold notebook files.
  • [EXTERNAL_DOWNLOADS]: The skill installs well-known libraries jupyterlab and ipykernel from public package registries.
  • [PROMPT_INJECTION]: The skill facilitates the editing and refactoring of existing Jupyter notebooks, creating a surface for indirect prompt injection.
  • Ingestion points: Existing .ipynb files are ingested when the agent is asked to refactor or edit them (SKILL.md).
  • Boundary markers: There are no explicit markers or instructions to ignore embedded commands within the ingested notebooks.
  • Capability inventory: The skill utilizes uv run and uv pip to execute Python code and install packages.
  • Sanitization: No sanitization or validation of the ingested notebook's cell content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 01:53 PM