The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill instructs the agent to load .env files from the project root using the find_dotenv() function. This involves accessing sensitive configuration files that typically contain API keys and trade secrets.
[COMMAND_EXECUTION]: The skill generates and writes a complete Python script (.py) to the local filesystem. While it uses the Write tool, the generated script is intended for subsequent execution, and its content is partially determined by unvalidated user input.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it handles untrusted data.
Ingestion points: The skill ingests user input through the $ARGUMENTS variable (strategy, symbol, exchange, interval).
Boundary markers: There are no boundary markers or instructions to ignore embedded commands within the user arguments.
Capability inventory: The skill uses the Write and Bash tools to create and manage the backtesting environment.
Sanitization: There is no explicit requirement for the agent to sanitize or validate the arguments before using them to create directories or name files (e.g., backtesting/{strategy_name}/).

backtest