financial-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (e.g.,
scripts/ratio_calculator.py,scripts/dcf_valuation.py) to process financial datasets. This is the primary intended functionality of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from JSON files, which represents an indirect prompt injection surface if the data contains malicious content.
- Ingestion points: External financial data files (
sample_financial_data.json,valuation_data.json, etc.) provided as arguments to the scripts mentioned inSKILL.md. - Boundary markers: The skill defines a mandatory data validation phase (Phase 2) to identify missing fields or implausible values before processing.
- Capability inventory: Local script execution and file reading for calculations and reporting.
- Sanitization: The workflow includes explicit steps for validating input data completeness and performing sanity checks on outputs against industry benchmarks.
Audit Metadata