The Agent Skills Directory

[SAFE]: The skill is designed for financial modeling and risk assessment. All provided files, including the Python script, focus on the stated purpose of credit loss computation.
[COMMAND_EXECUTION]: The skill includes a Python script (scripts/calculate.py) used for mathematical computations. Analysis of the code shows it is limited to standard arithmetic functions and data structure handling. It does not import or use dangerous modules for system-level access, process management, or shell execution.
[DATA_EXFILTRATION]: No network-enabled tools or commands (e.g., curl, wget, requests) are used. The skill does not attempt to access sensitive file paths or environment variables.
[EXTERNAL_DOWNLOADS]: The skill does not download or execute any remote scripts or packages. All logic is contained within the provided local scripts.
[PROMPT_INJECTION]: The instructions in SKILL.md define a clear professional role and operational parameters without attempting to override safety guidelines or extract underlying system prompts.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external financial data (such as CSV files), its capabilities are restricted to mathematical processing within a local script, presenting a negligible risk surface.

ecl-computation