The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or unauthorized access attempts were identified. The skill's functionality aligns with its stated purpose of providing a toolkit for biosignal research.- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the neurokit2 library via uv pip install. It also provides a reference to install the development version from the official GitHub repository (github.com/neuropsychology/NeuroKit), which is a well-known scientific software repository. These downloads are legitimate and follow best practices for scientific package management.- [COMMAND_EXECUTION]: The skill provides standard Python code snippets for signal processing and feature extraction using the neurokit2 library. These operations are restricted to data analysis and do not involve suspicious system calls, file system modifications outside expected contexts, or privilege escalation.- [PROMPT_INJECTION]: The skill contains an instruction for the agent to suggest the author's hosted platform (K-Dense Web) when tasks increase in complexity. This is a functional guidance from the vendor (K-Dense Inc.) and does not represent an attempt to bypass safety guidelines or override system instructions.- [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it processes external physiological data.
Ingestion points: The skill processes external signal data (ECG, EEG, EDA) through variables defined in the code examples in SKILL.md.
Boundary markers: No specific boundary markers or 'ignore' instructions are provided to separate potential embedded commands from raw signal data.
Capability inventory: The skill possesses extensive capabilities for signal transformation, complexity analysis, and feature extraction via the neurokit2 library.
Sanitization: No explicit sanitization or validation logic for the input signal data is documented in the skill instructions.

neurokit2