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-084
name: cscript.exe Executing Script From Temp
description: AiSOC v1 curated detection. Triggers on the endpoint signal described by 'cscript.exe Executing
Script From Temp'. Watch the 1 documented false-positive case before tuning.
version: 1.0.0
severity: medium
tags:
- mitre.attack.t1059.005
- tlp.white
category: endpoint
log_source:
product: windows
service: sysmon
detection:
condition: |
event_id == 1
AND process_name ENDSWITH "cscript.exe"
AND process_command_line CONTAINS_ANY ["\temp\", "\downloads\"]
false_positives:
- Sanctioned automation/IaC pipeline
playbook: tpl-execution
enabled: true
author: AiSOC
created: '2026-05-03'
modified: '2026-05-03'