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-application-001
name: SQL Injection Attempt in HTTP Query
description: Detects HTTP requests containing common SQL injection payload patterns in query strings or
POST bodies. Strong indicator of automated probing or active exploitation against web applications.
version: 1.0.0
severity: high
tags:
- mitre.attack.t1190
- tlp.white
category: application
log_source:
product: waf
service: http
detection:
condition: |
request_uri PATTERN_MATCH_ANY ["UNION SELECT", "OR '1'='1", "; DROP TABLE", "1=1--", "sleep\(", "benchmark\("]
false_positives:
- Security-research / pen-test traffic (allowlist src)
playbook: tpl-webattack
enabled: true
author: AiSOC
created: '2026-05-03'
modified: '2026-05-03'