Cybersecurity SOC RAG RAG Tools

Tools for security operations center (SOC) automation, incident response, and threat analysis using RAG. Focuses on SIEM integration, log analysis, security questionnaires, and cyber threat intelligence. Does NOT include general security tools without RAG, non-SOC cybersecurity applications, or drone/network-level security systems without SOC operations context.

There are 87 cybersecurity soc rag tools tracked. 2 score above 50 (established tier). The highest-rated is LLAMATOR-Core/llamator at 58/100 with 201 stars and 275 monthly downloads.

Get all 87 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=rag&subcategory=cybersecurity-soc-rag&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

# Tool Score Tier
1 LLAMATOR-Core/llamator

Red Teaming python-framework for testing chatbots and GenAI systems.

58
Established
2 kelkalot/simpleaudit

Allows to red-team your AI systems through adversarial probing. It is...

50
Established
3 sleeepeer/PoisonedRAG

[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to...

48
Emerging
4 SecurityClaw/SecurityClaw

A modular, skill-based autonomous Security Operations Center (SOC) agent...

46
Emerging
5 JuliusHenke/autopentest

CLI enabling more autonomous black-box penetration tests using Large...

43
Emerging
6 rohansx/cloakpipe

Privacy middleware for LLM & RAG pipelines - consistent pseudonymization,...

42
Emerging
7 AnubhavChoudhery/cybersec-scanner

A comprehensive, modular security scanning toolkit for detecting secrets,...

42
Emerging
8 AI-secure/AgentPoison

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM...

38
Emerging
9 taladari/rag-firewall

Client-side retrieval firewall for RAG systems — blocks prompt injection and...

38
Emerging
10 CaviraOSS/SecuPrompt

Protect your AI from Prompt Injection

35
Emerging
11 olegnazarov/rag-security-scanner

RAG/LLM Security Scanner identifies critical vulnerabilities in AI-powered...

34
Emerging
12 olegnazarov/llm-fortress

Enterprise AI Security Platform - Real-time firewall protection for LLM...

32
Emerging
13 toxy4ny/redteam-ai-benchmark

Red Team AI Benchmark: Evaluating Uncensored LLMs for Offensive Security

32
Emerging
14 clab60917/RAG-LLM-SOC_analyst

SOC Analyst Level 1 Replacement using RAG LLM

30
Emerging
15 LauJames/Topic-FlipRAG

[USENIX Security 2025] Topic-FlipRAG: Topic-Orientated Adversarial Opinion...

29
Experimental
16 cisco-ai-defense/adversarial-hubness-detector

Scanner for adversarial hubs in RAG and vector databases

26
Experimental
17 Curtis-Thomas/junction-sentinel

Junction Sentinel is a secure, multi-agent system designed to address drone...

26
Experimental
18 Har1sh-k/SecLint

A Python-based AI agent for detecting insecure code patterns in Python...

25
Experimental
19 StruggleY/Fo-Sentinel-Agent

企业级安全智能研判平台-多 Agent 协同与 Supervisor-Worker 深度思考架构驱动,集成全链路...

25
Experimental
20 jone0709/Securing-AI-ML-Maturity-Model

AI Operations Security Maturity Model and toolkit to secure AI/ML...

24
Experimental
21 HydroXai/pii-masker

PII Masker is an open-source tool for protecting sensitive data by...

24
Experimental
22 byerlikaya/Septum

Privacy‑first AI middleware that anonymizes PII locally and only sends...

24
Experimental
23 scthornton/semantic-chameleon

Dual-Stage Temporal Poisoning Attack on RAG Systems

24
Experimental
24 DonkeyKing01/SCSI-SLM-EV-Design

Official implementation of the SCSI-SLM framework for translating EV...

23
Experimental
25 prompt-security/RAG_Poisoning_POC

Stealthy Prompt Injection and Poisoning in RAG Systems via Vector Database Embeddings

23
Experimental
26 Jeremy0219/cloudguard-rag

AI-powered RAG pipeline for querying cloud security frameworks using Azure...

23
Experimental
27 Zyrabit-tech/zyrabit-SLM

Sovereign AI Infrastructure for Enterprise RAG. Zero-Trust PII Sanitization,...

23
Experimental
28 javidahmed64592/cyber-query-ai

Ollama-powered cybersecurity assistant for ethical penetration testing and...

23
Experimental
29 McKern3l/RAGdrag-labs

Test lab for RAGdrag — vulnerable RAG target, sample results, and test suite

23
Experimental
30 Cyberfortress-Labs/Cyberfortress-Intelligent-SOC-Ecosystem

An Intelligent SOC Ecosystem that integrates SIEM, SOAR, and SmartXDR to...

22
Experimental
31 Kartik-Katkar/Malicious-Prompt-Filter-for-RAG-Database

GitHub repository for a tool that detects and filters malicious prompts...

22
Experimental
32 lowwkezer/shannon

🛡️ Automate web app pentesting with AI to find real exploits before...

22
Experimental
33 luq12-growagarden/Adversarial-Detection-Engineering-Framework

🔍 Enhance detection accuracy by identifying and mitigating False Negatives...

22
Experimental
34 Kelvin295/cloakpipe

Protect LLM data by detecting, masking, and unmasking personal information...

22
Experimental
35 julienmerconsulting/rag-poisoning-demo

🧪 5 faux documents suffisent pour corrompre 80% des réponses d'un RAG. Démo...

22
Experimental
36 112ab0058/ray

PromptGuard Research | AI Security & RAG Defense

22
Experimental
37 45ck/llm-agent-security-skills

LLM and agent security skill pack for prompt injection, tool permissions,...

22
Experimental
38 sandipkatel/Unified-InfoSec-QnA-Assistant

A full-stack RAG based AI-powered system to help InfoSec teams efficiently...

21
Experimental
39 musabdulai-io/llm-production-safety-scanner

CLI tool for testing production safety controls in LLM/RAG apps - prompt...

21
Experimental
40 mishabar410/RAGLeakLab

Deterministic security testing for RAG pipelines: measure retrieval-induced...

21
Experimental
41 deconvolute-labs/benchmarks

Reproducible security benchmarking for the Deconvolute SDK and AI system...

21
Experimental
42 Privalyse/privalyse-mask

Semantic PII Masking & Anonymization for LLMs (RAG). GDPR-compliant,...

21
Experimental
43 uuluul/AI-autonomous-SOC

AI-powered autonomous SOC pipeline featuring hybrid log ingestion,...

21
Experimental
44 scthornton/ai-security-analyst-rag

Build an AI Security Analyst Assistant with RAG! LEARN FROM SCRATCH

21
Experimental
45 MartinMilevVenelinova/rag-copilot-it-security

Internal RAG copilot for Helpdesk/SecOps: cited answers, strict “not found”...

20
Experimental
46 bx0-0/CyberVisionAI

Cyber Vision AI is an award-winning, open-source AI assistant for...

20
Experimental
47 SidereusHu/RAG-Shield

Defense-in-depth security framework for RAG systems: poison detection,...

20
Experimental
48 ayinedjimi/SOC-Assistant

RAG-Powered SOC Assistant - By Ayi NEDJIMI

19
Experimental
49 Laav0808/cybersecurity-rag-assistant

RAG-powered cybersecurity knowledge assistant using LangChain, Weaviate, and...

19
Experimental
50 Cyberfortress-Labs/cyberfortress-labs.github.io

A unified intelligent SOC ecosystem where SIEM, SOAR, OpenXDR, Threat...

19
Experimental
51 HyeonjeongHa/MM-PoisonRAG

Official PyTorch implementation of "MM-PoisonRAG: Disrupting Multimodal RAG...

18
Experimental
52 gbikram/ThreatIntelRAG

Experimental RAG that consumes Cyber Security articles via RSS

18
Experimental
53 SecureAI-Team/asb-security-schema

A unified security event schema for LLM, RAG, and Agent applications.

16
Experimental
54 gypark94/RAGprompt

Anomaly detection using RAG

16
Experimental
55 enesdanis00/theo-hide

🔒 Protect sensitive files during streams with Theo Hide, ensuring no...

15
Experimental
56 Dhy4n-117/AI_SOC_Analyst

A privacy-first, local AI assistant for SOC analysts and threat hunters....

15
Experimental
57 Sumukha87/aia-auditor

AI RAG system for cloud security auditing — Qwen 2.5 7B via Ollama, Qdrant...

15
Experimental
58 ducwuyy/DocSentinel

Detect security risks in documents and questionnaires using automated...

14
Experimental
59 HameshTiwari/Secure-AI-Financial-Auditor

Enterprise GenAI framework implementing architectural guardrails and PII...

14
Experimental
60 thiagov21/squad-sentinela

AI workflow automation platform using agents and RAG to transform...

14
Experimental
61 kikiuuw/CVE-2025-68921

🔍 Identify and understand the local privilege escalation vulnerability...

14
Experimental
62 404godd/CVE-2026-20841-PoC

🛠 Demonstrate remote code execution in Windows Notepad versions below...

14
Experimental
63 hamzamalik3461/CVE-2026-20841

🛠 Demonstrate remote code execution in Windows Notepad via markdown links...

14
Experimental
64 ChangYeongJeong1103/prompt-injection-gatekeeper

Multi-stage prompt injection detection pipeline for RAG-based LLM agents

14
Experimental
65 brittytino/cyber-sop-assistant

A fully local Cybercrime SOP assistant for India, combining a FastAPI...

14
Experimental
66 stlin256/FraudSMS_RAG_Shield

融合大模型推理与RAG检索增强的诈骗短信甄别系统

14
Experimental
67 laricko/prompt-guard

Prompt-safety guards as a Python library. TF-IDF, RAG, LLM as a judge pipeline

14
Experimental
68 MAEN1-prog/CVE-2025-2304

🛠️ Exploit CVE-2025-2304 in Camaleon CMS easily with this Python script for...

14
Experimental
69 fartlover37/CVE-2026-2441-PoC

Demonstrate a proof-of-concept exploit for CVE-2026-2441, a high-risk Chrome...

14
Experimental
70 MadDataQualcommHackathon/SentinelAI

Enterprises in legal, defense, and finance cannot use AI on their most...

13
Experimental
71 nimad70/VulRAG

Investigating the vulnerability of Large Language Models (LLMs) to...

12
Experimental
72 Sai-Chakradhar-Mahendrakar/SOC-Analyst-Automation-using-RAG-Model

SOC Analyst Automation using a RAG model integrates a knowledge retrieval...

12
Experimental
73 Arthurfert/SecLLM-Gen

Offensive & Defensive cybersecurity LLM application

12
Experimental
74 butlerem/vulnerability-scanner-UniXcoder-RAG

AI-powered browser-based vulnerability scanner using UniXcoder embeddings...

11
Experimental
75 michealimuse777/Sentinel-Bot-Showcase

Sentinel: A Level 4 Autonomous Discord Agent. Features RAG-powered web...

11
Experimental
76 Ravi0529/isea-rag-attack-classification

Pipeline converts raw logs into structured session intelligence and maps...

11
Experimental
77 ddihora1604/FINAL_year_project

A whitebox LLMOps framework designed to enhance security and transparency in...

11
Experimental
78 danifeb94/ai-log-hunter

🛡️ AI Log Hunter v5.2 | Advanced Local RAG & Hybrid OCR (Llama 3 +...

11
Experimental
79 bhattaraisubal-eng/RAG-poisoning

A simple experiment on how RAG poisoning attack propagates through a...

11
Experimental
80 cyber-evangelists/threat-mon-rag

Threat Mon Rag to Demonstrate the Rag for security researchers.

11
Experimental
81 mizazhaider-ceh/Prime-PenTrix

AI Cybersecurity Learning Platform. Features Hybrid RAG (pgvector + BM25),...

11
Experimental
82 aliozen0/sentinel-io

Decentralized compute orchestration using AI agents (FastAPI, Next.js, RAG)....

11
Experimental
83 YangYang-Research/whale-sentinel-controllers

The Whale Sentinel Controllers

11
Experimental
84 agloriousli/SentinelAI

A security-focused Agent that ingests raw security logs, uses RAG to query...

11
Experimental
85 ReaperZ0v/sentinel-ai

A RAG implementation concept for law enforcement to search through their...

11
Experimental
86 r00tb3/RAG-Poisoning-Lab

RAG Poisoning Lab — Educational AI Security Exercise

11
Experimental
87 CyberSecAI/CWE-Expert

A CWE-Expert can be built for free in a browser in less than 1 minute using...

10
Experimental

Comparisons in this category