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
**/*.ipynbglob pattern as specified inSKILL.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, andEdittools, can execute thescripts/main.cjsNode.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