Security checks across malware telemetry and agentic risk
This is a local document-search skill whose indexing, Office conversion, and saved indexes match its stated audit-case purpose, but the generated files can contain sensitive case text.
Install this in an isolated virtual environment, index only case folders you intend to process, and keep the output directory private. Treat generated manifest, converted PDFs, and joblib indexes as sensitive because they can contain extracted audit text; do not commit or share them. Use a trusted LibreOffice installation and consider sandboxing conversion for documents from untrusted sources.
# Local-first audit/investigation RAG (no cloud APIs) fastembed>=0.3.0 scikit-learn>=1.5.0 pypdf>=4.2.0 pandas>=2.2.0
# Local-first audit/investigation RAG (no cloud APIs) fastembed>=0.3.0 scikit-learn>=1.5.0 pypdf>=4.2.0 pandas>=2.2.0 openpyxl>=3.1.2
# Local-first audit/investigation RAG (no cloud APIs) fastembed>=0.3.0 scikit-learn>=1.5.0 pypdf>=4.2.0 pandas>=2.2.0 openpyxl>=3.1.2 pyyaml>=6.0.1
fastembed>=0.3.0 scikit-learn>=1.5.0 pypdf>=4.2.0 pandas>=2.2.0 openpyxl>=3.1.2 pyyaml>=6.0.1 joblib>=1.3.0
scikit-learn>=1.5.0 pypdf>=4.2.0 pandas>=2.2.0 openpyxl>=3.1.2 pyyaml>=6.0.1 joblib>=1.3.0 numpy>=1.26.0
pypdf>=4.2.0 pandas>=2.2.0 openpyxl>=3.1.2 pyyaml>=6.0.1 joblib>=1.3.0 numpy>=1.26.0
pandas>=2.2.0 openpyxl>=3.1.2 pyyaml>=6.0.1 joblib>=1.3.0 numpy>=1.26.0
openpyxl>=3.1.2 pyyaml>=6.0.1 joblib>=1.3.0 numpy>=1.26.0
59/59 vendors flagged this skill as clean.
