getitune-training-a-model
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the library's official CLI tool
getitunefor training, testing, and prediction tasks. It also references thejustcommand runner for standard development workflows like linting and unit testing. These operations are restricted to the local development environment. - [EXTERNAL_DOWNLOADS]: The documentation includes instructions to use
uv syncfor environment setup and dependency management. This is a well-known, standard practice for Python project synchronization. - [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface by instructing the agent to process external datasets and checkpoint files.
- Ingestion points: Dataset root directories (COCO, YOLO, VOC formats) and model weight files (.pt checkpoints).
- Boundary markers: None identified in the prompt templates.
- Capability inventory: Subprocess execution via
getituneCLI and file system writes to the specifiedwork_dir. - Sanitization: No specific sanitization or validation of the dataset content or checkpoint integrity is described in the instructions.
- Assessment: While this is a standard requirement for ML training skills, processing untrusted data remains an inherent risk factor.
Audit Metadata