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-005
name: PowerShell with Encoded Command and Bypass Flag
description: AiSOC v1 curated detection. Triggers on the endpoint signal described by 'PowerShell with
Encoded Command and Bypass Flag'. Watch the 1 documented false-positive case before tuning.
version: 1.0.0
severity: high
tags:
- mitre.attack.t1059.001
- mitre.attack.t1027
- tlp.white
category: endpoint
log_source:
product: edr
service: process-create
detection:
condition: |
image_basename == "powershell.exe"
AND command_line CONTAINS_ALL ["-enc", "-exec"]
AND command_line CONTAINS_ANY ["bypass", "unrestricted"]
false_positives:
- Vendor management agents (allowlist by signed publisher)
playbook: tpl-malware-execution
enabled: true
author: AiSOC
created: '2026-05-03'
modified: '2026-05-03'