The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (generate_report_from_json.py and enrich_ips.py) to process gathered data and generate structured reports. This is part of the primary functional design for transforming raw log data into readable security analysis.
[SAFE]: The skill enforces a mandatory workspace selection process, requiring explicit user confirmation before executing queries if multiple Sentinel environments are detected. This prevents accidental data leakage or unauthorized access across different tenants.
[SAFE]: The instructions utilize specific, scoped MCP tools for Microsoft Graph and Sentinel queries, following best practices for targeted data retrieval rather than broad, unrestricted access.

user-investigation