dcf-model
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes financial data retrieved from external web sources and MCP servers, which creates a potential surface for indirect prompt injection.
- Ingestion points: Data is fetched from MCP servers and web searches as described in Step 1 of the workflow in SKILL.md.
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the retrieved data.
- Capability inventory: The skill can write to the local filesystem using the openpyxl library and execute local Python scripts for validation and recalculation.
- Sanitization: There is no evidence of content sanitization or validation for the data retrieved from external sources before it is written into Excel cells or comments.
- [EXTERNAL_DOWNLOADS]: The skill includes the requests library to fetch data from external sources, such as historical financials and market data. It specifically references well-known services like SEC EDGAR for sourcing US filings.
- [COMMAND_EXECUTION]: The skill instructions require the execution of local Python scripts, specifically recalc.py and validate_dcf.py, to ensure the integrity and quality of the generated Excel workbooks.
- [DYNAMIC_EXECUTION]: The skill utilizes a validation script (validate_dcf.py) included in the package to programmatically inspect Excel models for formula errors and logical inconsistencies at runtime.
Audit Metadata