The Agent Skills Directory

[SAFE]: The skill's functionality is focused on processing financial data within the local workspace. It does not attempt to access sensitive system files (e.g., .ssh, .aws, .env), perform network exfiltration, or bypass safety guidelines.
[COMMAND_EXECUTION]: The skill includes a bash command to discover relevant data files. This command uses standard Unix utilities ('find', 'grep', 'xargs') and is restricted to searching for non-sensitive file types (.md, .csv) within the current project directory. This is an expected and benign use of the tool to gather context for financial modeling.
[DATA_EXPOSURE]: The skill searches for financial metrics like ARR, MRR, and burn rate to populate its models. This data ingestion is handled locally and there are no patterns suggesting the movement of this data to external or untrusted destinations.

mint-model