The Agent Skills Directory

[SAFE]: The skill provides legitimate tools for financial modeling, including ratio calculation, DCF valuation, and forecasting. The accompanying Python scripts in the scripts/ directory were audited and found to perform only intended mathematical operations using standard modules like math and statistics. No unauthorized network access, file system modifications, or credential harvesting patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes financial data from JSON files, creating an ingestion surface for potential indirect prompt injection through data fields like item names or descriptions.
Ingestion points: Data is loaded from user-specified JSON files in scripts/ratio_calculator.py, scripts/dcf_valuation.py, scripts/budget_variance_analyzer.py, and scripts/forecast_builder.py.
Boundary markers: The scripts output analysis results as plain text or JSON without specific delimiters to isolate data from instructions.
Capability inventory: The scripts are limited to mathematical calculations and report generation; they do not have access to network tools, file-writing functions, or shell execution.
Sanitization: Input strings are parsed via standard JSON libraries and included in output reports without specific sanitization against instruction injection.

financial-analyst