cyber-security-llm-agents
A collection of agents that use Large Language Models (LLMs) to perform tasks common on our day to day jobs in cyber security.
- 405
- Jupyter Notebook
- 3 y ago
A collection of agents that use Large Language Models (LLMs) to perform tasks common on our day to day jobs in cyber security.
An AI-powered plugin for Caldera that orchestrates long-running LLM workflows to automatically create adversary emulation abilities and plan operations. Optionally enriches workflows with Retrieval-Augmented Generation (RAG) using Cyber Threat Intelligence (CTI) from STIX JSON files.
Aloha Water Treatment: a simulated water treatment plant with Modbus and BACnet, built as a target for MITRE Caldera for OT
Wildcat Dam: a simulated dam controller with Modbus, built as a target for MITRE Caldera for OT
Grid Watch: a simulated electrical grid outstation with DNP3, built as a target for MITRE Caldera for OT
Provides SAML authentication for CALDERA by establishing CALDERA as a SAML Service Provider (SP)
HVACSim: a simulated server room HVAC system with BACnet, built as a target for MITRE Caldera for OT
Evidence-driven purple team pipeline — extracts ATT&CK techniques from threat reports, executes adversary emulations (Caldera + Atomic Red Team), validates detections (LimaCharlie), and produces coverage reports with per-technique proof chains