aeon
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides standard installation instructions for the 'aeon' library using official package managers (pip and conda). It references the well-known 'aeon' toolkit which is a common resource for temporal data analysis.
- [SAFE]: The documentation in 'references/workflows.md' illustrates the use of 'pickle' and 'joblib' for model persistence. This is standard practice in the machine learning ecosystem for saving and loading trained models, and in this context, it is presented as a developer utility rather than an automated execution of untrusted data.
- [PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection through the processing of external time series data.
- Ingestion points: Data loading functions such as 'load_from_tsfile' and 'load_classification' mentioned in 'references/core_modules.md'.
- Boundary markers: None explicitly defined in the provided prompt templates for numerical data arrays.
- Capability inventory: The skill includes file-read/write operations ('load_from_tsfile', 'write_to_tsfile') and model serialization ('pickle.dump', 'joblib.dump').
- Sanitization: Relies on the standard data validation performed by the underlying NumPy, Pandas, and aeon libraries.
Audit Metadata