The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided notebook titles that are subsequently interpolated into markdown cells within the generated .ipynb file. This represents an attack surface for indirect prompt injection if the resulting notebook is later processed by an AI agent.
Ingestion points: The --title parameter in scripts/new_notebook.py receives untrusted input from the user.
Boundary markers: While the content is structured as JSON, there are no specific prompt instructions or delimiters used to ensure the agent ignores potentially malicious instructions embedded in the title string.
Capability inventory: The bundled script scripts/new_notebook.py has the capability to create directories and write files to the local file system using pathlib and json modules.
Sanitization: The skill includes a slugify function to sanitize filenames (enforcing alphanumeric characters and hyphens), but the title itself is not sanitized before being placed into the markdown cell content.
[COMMAND_EXECUTION]: The skill workflow requires the execution of shell commands, specifically using uv run to invoke the bundled scaffolding script and uv pip install for managing notebook dependencies. These operations are essential for the skill's primary purpose and are performed on the local system.

jupyter-notebook