backtest-assumption-check
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and supporting Python scripts are entirely focused on the analysis and quality control of quantitative trading models. The repository includes clear documentation and a self-test utility to verify its auditing capabilities.
- [COMMAND_EXECUTION]: The skill includes local Python scripts (audit_cli.py and various detectors) for data processing. These scripts use standard, well-known libraries like pandas and numpy to perform statistical analysis on user-supplied CSV or Parquet files. No unauthorized or suspicious command patterns were found.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external strategy code and research reports, it provides a rigid 7-step workflow and a nine-axis audit framework. This structured approach ensures the agent remains focused on data validation and evidence gathering, mitigating the risk of instructions within the audited material influencing the agent's behavior.
Audit Metadata