backtest-expert
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill contains no instructions or code for network access, data exfiltration, or remote downloads. All operations are performed locally on the user's filesystem.
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/evaluate_backtest.pyintended for execution. This script performs mathematical scoring of trading metrics. It uses only standard Python libraries and implements strict input validation to ensure that all parameters are valid numeric types. - [SAFE]: The skill's instructions in
SKILL.mdand reference documents follow best practices for systematic trading and do not contain any prompt injection or behavioral override patterns. - [SAFE]: The included test suite (
scripts/tests/) demonstrates a high level of code quality and verifies the security boundaries of the evaluation script, such as handling invalid inputs.
Audit Metadata