financial-analyst
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill handles external JSON data files, which presents a surface for indirect prompt injection. 1. Ingestion points: JSON files (e.g., sample_financial_data.json) are processed by scripts in the scripts/ folder. 2. Boundary markers: No explicit delimiters or isolation instructions are provided for handling external content. 3. Capability inventory: The skill is restricted to financial calculations and report generation, with no network access or system-level modification tools. 4. Sanitization: Data is validated for completeness and sanity during the modeling phase.
- [SAFE]: No malicious patterns, obfuscation, or risky dependencies were detected. The skill relies exclusively on the Python standard library.
Audit Metadata