three-statement-model-builder
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- Standard Input Processing: The skill ingests a
plan.jsonfile as its primary configuration source. To ensure data integrity, it utilizes a dedicated validation utility (validate_plan.py) that checks for schema compliance and logical consistency before processing. - Custom Runtime Loader: The implementation uses a custom loading mechanism in
runtime_loader.pyto execute core logic from internal files. This design pattern is used to organize the skill's complex financial logic while maintaining a clean execution surface. - Programmatic Workbook Generation: The skill automates the creation of Excel deliverables by patching XML components within bundled templates. This process is handled using standard libraries and avoids the need for external third-party dependencies for file manipulation.
- Comprehensive Audit Trail: The tool generates detailed execution logs, manifests, and citation ledgers (
model_citations.json) for every build. This provides full transparency into how model outputs are derived from the input data, supporting auditability and senior review workflows.
Audit Metadata