Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
Python agentic-aiai-securityalert-triageblue-teamcybersecuritydetection-engineeringincident-responselanggraphllm-agentsmcpmitre-attackmodel-context-protocolpurple-teamsecurity-operationsself-hostedsiemsoarsocthreat-detectionthreat-intelligence
id: det-endpoint-004
name: Office Application Spawns Shell or Scripting Engine
description: AiSOC v1 curated detection. Triggers on the endpoint signal described by 'Office Application
Spawns Shell or Scripting Engine'. Watch the 1 documented false-positive case before tuning.
version: 1.0.0
severity: high
tags:
- mitre.attack.t1059
- mitre.attack.t1204.002
- tlp.white
category: endpoint
log_source:
product: edr
service: process-create
detection:
condition: |
parent_image_basename IN ["winword.exe", "excel.exe", "powerpnt.exe", "outlook.exe"]
AND image_basename IN ["powershell.exe", "cmd.exe", "wscript.exe", "cscript.exe", "mshta.exe"]
false_positives:
- Legitimate macros (rare; tag with macro-allowlist)
playbook: tpl-malware-execution
enabled: true
author: AiSOC
created: '2026-05-03'
modified: '2026-05-03'