financials-normalizer

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • Data Processing Workflow: The skill coordinates several local Python scripts to transform, normalize, and validate financial data from source materials into standardized CSV and XLSX outputs. This represents a well-structured approach to data management.
  • Subprocess Execution: The skill invokes specific local scripts (normalize_extracted_financials.py, validate_normalized_financials.py) to perform its core functions. These scripts utilize standard Python libraries for file I/O and data parsing, such as csv and json.
  • Input Ingestion: The skill is designed to ingest user-provided financial documents (PDFs, XLSX, CSV). While this constitutes an indirect prompt injection surface, the risk is addressed through explicit validation scripts and QA protocols defined in the reference documentation.
  • Credential Management: No hardcoded credentials or unsafe secret handling practices were identified. The skill correctly instructs users to manage source reliability and freshness through a source index.
  • Resource Management: The skill references shared workflow components (e.g., ../../shared/workflow-source-resolution.md), which is standard practice for modular skill architectures within the vendor's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 06:12 AM
Security Audit — agent-trust-hub — financials-normalizer