getitune-training-a-model

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the getitune library and points to official Intel documentation (docs.geti.intel.com), which are recognized as well-known and trusted sources for the intended machine learning workflow.\n- [COMMAND_EXECUTION]: The skill uses the uv package manager for environment setup and the getitune CLI for model training. These commands are standard for the skill's purpose and do not perform suspicious or unauthorized operations.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external computer vision datasets for model training. This represents a functional data ingestion surface.\n
  • Ingestion points: Dataset paths provided to the data parameter in the Python API and --data_root in the CLI as documented in SKILL.md.\n
  • Boundary markers: None explicitly specified for the raw dataset content.\n
  • Capability inventory: Local file reading, model training, and evaluation using the getitune library (SKILL.md).\n
  • Sanitization: Relies on the getitune library and the Datumaro framework for dataset format validation and auto-detection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 01:43 PM
Security Audit — agent-trust-hub — getitune-training-a-model