3-statement-model
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, which creates a potential surface for indirect prompt injection.
- Ingestion points: Processes user-provided Excel templates and extracts data from external SEC EDGAR filings as described in references/sec-filings.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the ingested financial data to prevent the execution of embedded prompts.
- Capability inventory: The skill uses the openpyxl library for file system writes and instructions indicate the agent should execute a local Python script for workbook recalculation.
- Sanitization: There is no mention of sanitization or validation logic for the content extracted from SEC filings or user-provided templates.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script to handle Excel recalculation logic (e.g., 'python /path/to/excel-author/scripts/recalc.py ./out/model.xlsx').
- [EXTERNAL_DOWNLOADS]: The skill is configured to fetch financial data and regulatory filings from the official SEC EDGAR system (sec.gov) and references commercial financial data providers including FactSet, Daloopa, and Kensho.
Audit Metadata