hebrew-ml-datasets-navigator

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily informational, providing high-quality reference material for researchers and developers in the Hebrew NLP ecosystem.
  • [EXTERNAL_DOWNLOADS]: Includes references to numerous datasets and models hosted on HuggingFace and GitHub. These originate from well-known organizations such as ivrit.ai, Dicta, and the Israeli National NLP Program. All links were verified as legitimate and relevant to the skill's purpose.
  • [COMMAND_EXECUTION]: Provides a Python script (scripts/find_dataset.py) for interactive dataset selection. The script's logic is transparent, only involves filtering a hardcoded JSON catalog, and performs no network or sensitive file operations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 01:24 PM
Security Audit — agent-trust-hub — hebrew-ml-datasets-navigator