jupyter-notebook-best-practices

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify Jupyter Notebook files (.ipynb), which may contain untrusted code or text that could influence agent behavior.
  • Ingestion points: The skill targets all files matching the **/*.ipynb glob pattern as specified in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific 'ignore' markers to separate notebook content from the agent's instructions.
  • Capability inventory: The agent has access to Read, Write, and Edit tools, can execute the scripts/main.cjs Node.js script, and is instructed to use shell commands (cat) for memory management.
  • Sanitization: No sanitization or validation logic is implemented to filter or escape instructions within the notebook files before they are processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 02:59 AM