The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted input from user arguments and local configuration files, which could potentially be used to influence the generated strategy code.\n
Ingestion points: $ARGUMENTS (template, underlying, expiry-date) and local configuration files like algo-expert/rules/options-execution.md and algo-expert/rules/assets/<template>/strategy.py.\n
Boundary markers: None; the skill does not use specific delimiters to separate user input from the rest of the prompt logic.\n
Capability inventory: The skill is configured with Read, Write, Edit, Bash, Glob, and Grep tools.\n
Sanitization: No validation or sanitization of user-supplied parameters is implemented before they are used in the code generation process.\n- [DYNAMIC_EXECUTION]: The skill generates executable Python scripts by copying and modifying local templates at runtime.\n
Evidence: Instructions direct the agent to "Create strategies/<template>_<underlying>/ and copy + customize" strategy templates, incorporating variables such as UNDERLYING, LOTS, and SL_MULTIPLIER directly into new .py files.

algo-options