The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides snippets for using jupyter nbconvert to execute notebooks. Specifically, the command jupyter nbconvert --to notebook --execute --inplace notebook.ipynb triggers the execution of all code cells within the target file.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes content from external .ipynb files without safety boundaries.
Ingestion points: Notebook content is loaded into the agent's context using json.load in Python snippets and grep in shell snippets.
Boundary markers: No delimiters or safety instructions are defined to separate notebook content from agent instructions.
Capability inventory: The skill uses subprocess calls to execute notebook code and provides Python snippets to write modified content back to the file system.
Sanitization: There is no logic to sanitize or validate the content of the cells before they are processed or executed.

jupyter