creating-financial-models
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted external financial data which creates an attack surface for indirect prompt injection. 1. Ingestion points: Historical financial statements and user-supplied revenue/growth assumptions. 2. Boundary markers: Absent from the provided documentation. 3. Capability inventory: Local execution of dcf_model.py and sensitivity_analysis.py calculation scripts. 4. Sanitization: No input validation or sanitization is mentioned for the financial data processed.
Audit Metadata