data-science-interactive-apps

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides installation instructions for a wide range of standard data science and visualization packages from PyPI, such as streamlit, gradio, panel, and scikit-learn. It also mentions downloading the Quarto publishing system from its official site (quarto.org).\n- [COMMAND_EXECUTION]: Documentation includes examples of running framework-specific CLI tools, including streamlit run, panel serve, bokeh serve, and voila. These are standard commands for building and serving the respective application types.\n- [REMOTE_CODE_EXECUTION]: A reference file demonstrates loading local machine learning models using pickle.load. While pickle should be used with caution for untrusted files, it is a standard practice for local model persistence in the machine learning community.\n- [CREDENTIALS_UNSAFE]: The skill includes explicit warnings against hardcoding secrets and demonstrates the use of Streamlit's secrets management and environment variables as secure alternatives.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 03:19 PM