Hunt Analytics Generation

• Use the available inputs, which may include:
  • System internals context
  • Adversary tradecraft context
  • The structured hunt hypothesis
  • Suggested or identified data sources
• Confirm the specific adversary behavior to be modeled.
• If critical context is missing, request minimal clarification before proceeding.

This step is complete when the behavior to be modeled is clearly understood. Do NOT read reference documents during this step.

Step 2: Generate Analytic Candidates (repeat up to 5 times)

For each analytic candidate:

• Select the most relevant data source or sources from the available list.
• Use MS Sentinel.search_tables to retrieve schema details for the selected tables.
• Review schemas to understand available fields and attributes.
• Identify the key entities involved (e.g., process, user, host, registry key, IP).
• Model the behavior as relationships or sequences between entities, using a graph-like view to represent how the activity unfolds and the conditions that matter.
• Ground the logic by mapping entities and conditions to schema fields.
• Capture a query-style representation, using SQL-like logic, that expresses analytic intent without execution.

Do NOT determine whether the behavior is suspicious or anomalous. Do NOT write executable queries. Do NOT read reference documents during this step.

Step 3: Produce Analytics Summary

Produce a final summary of the generated analytics.

• Structure the output using references/analytic-template.md.
• Repeat the template for each analytic.
• Clearly separate:
  • Behavioral reasoning
  • Schema grounding
  • Query-style representation

Do NOT include execution logic, thresholds, or validation steps.3a:["$","$L43",null,{"content":"$44","frontMatter":{"name":"hunt-analytics-generation","description":"Generate query-agnostic analytics that model adversary behavior by translating hunt investigative intent into analytic definitions grounded in schema semantics. This skill is used to define how behavior should manifest in data before query execution or validation, and works best when informed by system internals, adversary tradecraft, a structured hunt focus, and suggested data sources.","metadata":{"short-description":"Generate analytics for hunt planning"}}}]