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.pylocated at$CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.pyto scaffold notebook files. - [EXTERNAL_DOWNLOADS]: The skill installs well-known libraries
jupyterlabandipykernelfrom 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
.ipynbfiles 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 runanduv pipto execute Python code and install packages. - Sanitization: No sanitization or validation of the ingested notebook's cell content is described.
Audit Metadata