The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill includes capabilities to ingest and process data from external files (TS, ARFF, TSV, CSV) and remote benchmark repositories. While these files typically contain numeric time series data, they represent a potential surface for indirect prompt injection if malicious instructions are embedded in metadata or labels. 1. Ingestion points: The 'datasets_benchmarking.md' file specifies various file loaders and remote dataset fetchers. 2. Boundary markers: The skill does not define specific prompt boundaries for data content, relying on the library's structured parsing. 3. Capability inventory: The skill uses Bash, Read, Write, and Edit tools. 4. Sanitization: Standard numeric parsing by the 'aeon' library provides implicit sanitization for the primary data payload.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download of the 'aeon' Python package from PyPI and benchmark datasets from established research platforms like Zenodo and the UCR/UEA Time Series Archive. These references are standard for the data science domain and originate from reputable sources.
[COMMAND_EXECUTION]: The skill uses shell commands for environment setup and package management ('uv pip install'). These commands are restricted to the intended purpose of preparing the machine learning environment.

aeon