The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the development version of the NeuroKit2 library directly from a GitHub repository (https://github.com/neuropsychology/NeuroKit/zipball/dev). While this is a common practice for accessing the latest features of this library, the repository originates from a source that is not included in the pre-defined list of trusted organizations or well-known services.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external biosignal data (such as ECG, EEG, and EDA signals) which could potentially be used as a vector for indirect prompt injection if the processing logic is influenced by malicious patterns embedded in the data.
Ingestion points: External physiological signals are passed into processing functions like nk.ecg_process(), nk.eeg_power(), and nk.bio_process(), typically from user-supplied files or data streams.
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within the physiological data.
Capability inventory: The skill possesses extensive capabilities for signal transformation, peak detection, and complexity analysis, which could be leveraged if an injection were successful.
Sanitization: There are no documented steps for the sanitization or validation of the input signal data before it is processed by the toolkit.

neurokit2