The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires installation of third-party libraries including neurokit2, numpy, pandas, matplotlib, and scipy from the Python Package Index (PyPI).\n- [COMMAND_EXECUTION]: The instructions include shell commands to install dependencies using the pip package manager.\n- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates processing external data files, which creates a potential surface for indirect prompt injection where untrusted data could influence agent behavior.\n
Ingestion points: The skill loads external data from files (e.g., CSV recordings) using pd.read_csv in the batch processing and module example sections.\n
Boundary markers: The skill does not implement delimiters or specific instructions to ignore potentially malicious embedded content within the ingested data files.\n
Capability inventory: The skill uses file-writing capabilities through matplotlib.pyplot.savefig for generating reports and pandas.DataFrame.to_csv for saving extracted features.\n
Sanitization: No sanitization, filtering, or validation of the input data stream is provided prior to processing.

neurokit2