ds-notebook-strict-code
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are limited to output formatting and pedagogical guidance for data science tasks. No suspicious network activity or sensitive file access patterns were identified.
- [COMMAND_EXECUTION]: The documentation mentions a local script for exporting the skill to different platforms; this is a development utility and not a command the agent is instructed to run during user interactions.
- [PROMPT_INJECTION]: The skill contains specific activation conditions and formatting rules, but does not attempt to bypass safety filters or override system instructions in a malicious way.
Audit Metadata