backtest-expert
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified across the 10 threat categories. The skill's primary purpose is educational and analytical.
- [COMMAND_EXECUTION]: The skill includes a Python script (
evaluate_backtest.py) designed to be executed locally. The script processes user-provided numeric metrics and generates Markdown and JSON reports. It employs standard library functions for file operations and performs strict validation on input ranges. - [DATA_EXFILTRATION]: No network access, data transmission, or access to sensitive local files (such as credentials or configuration files) was observed.
- [EXTERNAL_DOWNLOADS]: The skill does not download any external packages or scripts. All logic is contained within the provided files.
- [PROMPT_INJECTION]: The instructional content follows best practices and does not contain any attempts to bypass agent safety filters or override system instructions.
Audit Metadata