CyberStrikeAI

CyberStrikeAI 中文 | English The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next. CyberStrikeAI connects planning, execution, human oversight, evidence, and replay in one auditable...

GhidrAssist

GhidrAssist Author: Jason Tang An advanced LLM-powered plugin for interactive reverse engineering assistance in Ghidra. Description GhidrAssist integrates Large Language Models LLMs into Ghidra to provide intelligent assistance for binary exploration and reverse engineering. It supports any OpenA...

Syd

Syd - Offline Penetration Testing Assistant Syd is an air-gapped penetration testing assistant that analyzes scan outputs using local LLMs and retrieval-augmented generation. It runs entirely on your laptop without requiring internet connectivity or API keys. Overview Syd parses technical scan...

ai-llm-red-team-handbook

AI / LLM Red Team Field Manual & Consultant's Handbook A comprehensive operational toolkit for conducting AI/LLM red team assessments on Large Language Models, AI agents, RAG pipelines, and AI-enabled applications. This repository provides both tactical field guidance and strategic consulting...

CamoDocs

CamoDocs Official repo of the EMNLP 2026 paper CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents. CamoDocs is a knowledge database poisoning attack against Retrieval-Augmented Generation RAG that needs no query inclusion. Each adversarial...

D-Scan

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse Official implementation of SIGIR 2026 paper When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse. D-SCAN is an analysis framework for detecting document poisoning attacks in RAG...

gha-lab-e8902eccd3

Automated research artifact — not the upstream project. This repository is a disposable lab built by an automated harness for a master's thesis at Université Laval on reproducing published GitHub Actions workflow vulnerabilities. It is a verbatim snapshot of timescale/pgai at commit...

Zetsu

A personal offline RAG system for offensive security knowledge. Ingest your writeups, lab solutions, bug bounty reports, and security blogs, then query them in natural language during engagements. No cloud, no SaaS, your knowledge stays yours. What it does ZETSU turns your accumulated knowledge...

SecurityClaw

SecurityClaw — Autonomous SOC Agentic Framework A modular, skill-based autonomous Security Operations Center SOC agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral memory, and validates real-time anomalies using LLMs. Features Skill Modularity — Capabilities as isolate...

aligned-rag-eval

AlignedRAG-Eval AlignedRAG-Eval is a lightweight evaluation harness for RAG poisoning defenses. It builds the four-condition record used in our paper: clean and poisoned inputs, each with and without a defense. From saved answer files, it reports prevented targets, introduced targets, net target...

Open WebUI < 0.9.5 - Information Disclosure

Open WebUI 0.9.5 contains an information disclosure vulnerability caused by unauthenticated access to GET /api/v1/retrieval/ endpoint, letting remote attackers retrieve live RAG pipeline configuration without authorization, exploit requires no authentication. id: CVE-2026-45397 info: name: Open...

PoisonCraft

PoisonCraft This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models. Overview POISONCRAFT aims to demonstrate how a malicious actor can plant “poisoned” content into the corpus used by Retrieval-Augmented...

KidnapRAG

KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation Systems 🎓 Paper | 📄 Datasets | 🚀 Quick Start Quick Start Run the following commands from the parent directory of the cloned KidnapRAG repository. cd KidnapRAG conda create -n KidnapRAG python=3.10 cond...

qlcoder

QLCoder Agentic Framework for Synthesizing CodeQL Queries Table of Contents Overview Installation Docker Recommended Native Linux Usage Quick Start Development Tooling Examples Paper Environment Contributions Team Citation Affiliated Projects Overview QLCoder is a framework for using LLMs to...

Awesome-RAG-Security

Awesome-RAG-Security News Initial release: This repository records papers on RAG security following the SLOT taxonomy from our survey. A Survey of Secure Retrieval-Augmented Generation Yuming Xu 1, Mingtao Zhang 1, Zhuohan Ge 1, Haoyang Li 1, Nicole Hu 1, Yongqi Zhang 2, Zhiyuan Wen 1, Jason Chen...

EUVD-2026-125609

ragent 1.0.0 through 1.1.0 contains a missing authorization vulnerability in RagTraceController that allows any logged-in user to view all users' RAG traces. Attackers can page through /rag/traces/runs and related node endpoints to read other users' usernames, user ids, conversation ids, question...

CVE-2026-129157

The software ragent versions 1.0.0 through 1.1.0 contains a missing authorization vulnerability in the RagTraceController component. This flaw allows any authenticated user to access and view RAG traces belonging to other users. By navigating the /rag/traces/runs and related node endpoints, an at...

VulTriage

An intelligent vulnerability detection framework based on Large Language Models and static code analysis, supporting multi-dataset evaluation and ablation studies. 📋 Table of Contents Introduction Key Features System Requirements Quick Start Usage Datasets & Models FAQ Introduction This project i...

OWASP-WSTG-Rag

OWASP WSTG RAG A Retrieval-Augmented Generation RAG system that indexes the OWASP Web Security Testing Guide WSTG into a vector database, providing instant access to security testing methodologies via REST API and MCP Model Context Protocol for Claude Code integration. Features Complete WSTG...

SecureAI-Scan

SecureAI-Scan An offline scanner for the code that talks to LLMs, MCP servers, vector stores, and Agent Skills. It finds prompt injection, MCP command injection and path traversal, RAG data leaks, and poisoned skills, and it proves each finding with a source → sink trace through your real imports...