The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute Python scripts that it generates at runtime. This is the intended functionality for performing the backtests and generating reports.
[PROMPT_INJECTION]: The skill processes the symbol input as a string, which is later interpolated into file paths and generated Python code. This represents a surface for indirect prompt injection or code injection if a user provides a malicious symbol string. However, other critical inputs like strategy and interval are strictly constrained by enums, and the overall risk is consistent with standard data analysis skills.

backtest