automl-hyperparameter-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external dataframes and datasets for model training, which provides a surface for indirect instructions if the data source is untrusted.
- Ingestion points: Dataframes (e.g., 'df' in SKILL.md) and generic datasets passed to model training and hyperparameter optimization functions.
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate data content from the agent's instruction context.
- Capability inventory: The skill demonstrates capabilities for executing Python code to perform model training, cross-validation, and hyperparameter search using various libraries (SKILL.md).
- Sanitization: No explicit data sanitization or input filtering is mentioned for the processed datasets.
Audit Metadata