The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess.run within its test suite (scripts/tests/test_futures_position_sizer.py) to verify CLI behavior. This is a standard development practice for automated testing and does not pose a risk during normal skill operation.
[DATA_EXFILTRATION]: The skill explicitly states and demonstrates an offline-only design. No network-capable libraries (like requests or urllib) are used, and no attempts to access sensitive system files (e.g., SSH keys, cloud credentials) were found.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or secrets were detected. The skill's primary purpose is pure mathematical calculation based on operator input.
[REMOTE_CODE_EXECUTION]: The skill does not download external code or scripts. It relies solely on the Python standard library and its own local scripts.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted JSON data (gate reports). It implements a 'hardened' loader that prevents resource exhaustion via RecursionError and sanitizes for non-finite floating-point values. Furthermore, the ingested data is used only for mathematical calculations, with no execution capabilities (like eval or exec) present in the processing logic.

futures-position-sizer