neurokit2
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides standard installation instructions for the
neurokit2library via PyPI and includes a link to the official project repository on GitHub for installing the development version. - [INDIRECT_PROMPT_INJECTION]: The skill processes external physiological signals, which represents a data ingestion surface.
- Ingestion points: Physiological signal data (ECG, EEG, RSP, etc.) is ingested by various processing functions such as
nk.ecg_process()andnk.eeg_power()inSKILL.mdand related reference files. - Boundary markers: None specific to prompt injection are present, as the tool is designed for numerical biosignal analysis.
- Capability inventory: The skill uses scientific computing libraries (NeuroKit2, MNE, Pandas) for signal processing. No capabilities for arbitrary shell execution, unauthorized file access, or network exfiltration were found.
- Sanitization: The skill leverages NeuroKit2's built-in signal cleaning and sanitization functions to validate input data.
Audit Metadata