hebrew-ml-datasets-navigator

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/find_dataset.py includes a function verify_licences_against_hub that uses subprocess.run to execute curl commands. This is a developer-facing utility designed to audit the internal catalog's licensing data against live records from a well-known service (HuggingFace).
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to the HuggingFace Hub API (huggingface.co/api/...) to retrieve metadata for verification. These requests target a well-known service and do not involve the execution of remote code or the exfiltration of sensitive data.
  • [NO_CODE]: The majority of the skill consists of instructional Markdown files, reference catalogs, and licensing guides aimed at helping researchers select appropriate datasets for Hebrew NLP tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 08:26 AM