financial-analyst

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local Python scripts (scripts/ratio_calculator.py, scripts/dcf_valuation.py, scripts/budget_variance_analyzer.py, scripts/forecast_builder.py) to perform financial calculations. These scripts are executed with user-provided JSON data files as arguments, which is standard behavior for data-driven agent tools.
  • [DATA_EXFILTRATION]: No network operations (such as curl, wget, or HTTP requests) were identified in the skill instructions. The skill does not attempt to access sensitive system files or credentials.
  • [REMOTE_CODE_EXECUTION]: The skill explicitly states it has no external dependencies and relies solely on the Python standard library. All executable scripts are local to the skill package; no code is downloaded from external or untrusted sources.
  • [PROMPT_INJECTION]: The skill instructions do not contain any attempt to override agent safety guidelines, bypass constraints, or extract system prompts. The provided guidelines focus on financial modeling rigor and documentation standards.
  • [DATA_EXPOSURE]: There are no hardcoded credentials, API keys, or exposure of sensitive environment variables in the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:05 PM
Security Audit — agent-trust-hub — financial-analyst