trading-strategy-backtest
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill follows a workflow where it generates a local Python script based on user-provided strategy parameters and then executes that script to perform backtesting calculations and generate result files.
- [PROMPT_INJECTION]: The skill parses untrusted natural language input from users to define strategy logic, which introduces an indirect prompt injection surface. The skill mitigates this risk by providing strict parsing checklists, separating signal generation from execution in code, and using DOMPurify for sanitizing user-visible dashboard content.
Audit Metadata