reasongate

ReasonGate A self-hostable gate that inspects the text going into and out of an LLM and returns an explainable allow / flag / block decision with a machine-readable audit record for every call. What this is The open-source core is rule-based. It does four things: recognizes known prompt-injection...

AWE

AWE: Adaptive Agents for Dynamic Web Penetration Testing Akshat Singh Jaswal · Ashish Baghel Accepted at NDSS LAST-X 2026 Abstract Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating softwa...

cerebro-red-v2

CEREBRO-RED v2 Research Edition Autonomous Local LLM Red Teaming Suite A research-grade framework for automated vulnerability discovery in local LLMs using Agentic Fuzzing and Adaptive Adversarial Mutation AAM. Research Goals Implement PAIR Algorithm Prompt Automatic Iterative Refinement from...

BoxPwnr

BoxPwnr LLM대규모 언어 모델이 CTF 챌린지와 보안 랩을 스스로 얼마나 해결할 수 있는지 확인해 보는 재미있는 실험입니다. HackTheBox에서 시작해 이제 많은 플랫폼과 에이전트형 솔버를 지원합니다. BoxPwnr은 다양한 에이전트형 아키텍처의 성능을 테스트하는 데 사용할 수 있는 플러그 앤 플레이 시스템을 제공합니다: --solver claudecode, codex, cursor-cli, grok, kirocli, external, singleloopxmltag, singleloop,...

skyvern

🐉 Автоматизируйте браузерные рабочие процессы с помощью LLM и компьютерного зрения 🐉 Skyvern автоматизирует браузерные рабочие процессы с помощью LLM и компьютерного зрения. Он предоставляет SDK, совместимый с Playwright, который добавляет AI-функциональность поверх playwright, а также конструкто...

SecureAI-Scan

SecureAI-Scan CLI offline que escanea TypeScript, JavaScript y Python en busca de riesgos de LLM, MCP, Agent Skill y RAG: evidencia de flujo de datos resuelta por imports, cero falsos positivos por defecto, mapeado a OWASP LLM/ASI/MCP Top 10. La mayoría de los escáneres en este ámbito buscan una...

CTFTiny

CTFTiny: Lite Benchmarking Offensive Cyber Skills in Large Language Models This is the official repository for CTFTiny from "Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark" AAAI'26 paper. For CTFJudge, please refer to CTFJud...

promptfoo

Promptfoo: оценка LLM и red teaming promptfoo — это CLI и библиотека для оценки и red teaming LLM-приложений. Прекратите метод проб и ошибок — начинайте создавать безопасные и надёжные AI-приложения. Веб-сайт · Начало работы · Red Teaming · Документация · Discord Promptfoo теперь часть OpenAI...

token-proxy

llm-token-proxy A transparent PII redaction proxy for LLM API traffic. Sits between your application and the LLM provider, pseudonymizing sensitive data on the way out and restoring it on the way back. Your LLM never sees real names, emails, IPs, or domains — it works entirely with structured...

FinRED-paper

FinRED: Financial Red-Teaming Evaluation Dataset A red-team benchmark generation pipeline for safety evaluation in the financial domain. Supplementary Documentation Detailed materials referenced in the paper: docs/expertvalidation.md — Per-question Focus Group Interview FGI results from the 12 FS...

ai-kill-chain

Extended Cyber Kill Chain for AI-Era Threats An update to the Lockheed Martin Cyber Kill Chain for defenders working against LLM and agentic AI attacks. Adds a pre-attack stage for model supply chain compromise. Adds AI-specific sub-techniques to each of the original seven stages. Splits the...

beelzebub

Beelzebub 디셉션 런타임 프레임워크 Beelzebub는 SSH, HTTP, TCP, TELNET, MCP 프로토콜 전반에 걸쳐 적응형 LLM 기반 데코이 서비스를 배포하는 오픈소스 디셉션 런타임입니다. 수동적인 허니팟을 넘어, 공격자와 현실적인 상호작용을 능동적으로 수행하여 고정밀 위협 인텔리전스를 수집하고 AI 에이전트에 대한 프롬프트 인젝션 공격을 탐지합니다. 목차 Beelzebub 목차 주요 기능 LLM 디셉션 데모 빠른 시작 인스톨러 로컬 Go Docker Helm Kubernetes 사용 CLI 참조...

r2ai

R2AI - radare2용 LLM 기반 증강 리버싱 ╭─────────────────────────────────╮ │ , . . , │ ╭──╮ │ : \ \ |: \ : | │ │ │ │ | |/ || , || : | │ │ O O r2ai -q explain: Explain the current function - devices: Find and explain devices used - libs: Group imports by Libraries - varnames: Better variable names -...

dataset

🚀 CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models 🛡️ The largest and most comprehensive Generative AI-based CyberSecurity-focused Dataset for Benchmarking Large Language Models 🌟 Overview The CySecBench paper offers: 🎯 A cutting-edge...

DonkAI

Hands-on lab for the OWASP Top 10 for LLM Applications 2025 - no real LLM required. DonkAI is deliberately vulnerable web app you can run in one command and use to learn how LLM-integrated systems get broken by actually breaking them. Every OWASP LLM Top 10 category is represented by at least one...

phantom-brain

PHANTOM BRAIN v0.9 ⚠️ Proyecto experimental — no para uso en producción. El análisis con IA asiste al investigador humano; no reemplaza una auditoría manual. Siempre verifica los hallazgos de forma independiente. Lo que ES y NO ES Phantom Brain ✅ Lo que ES| ❌ Lo que NO ES ---|--- Analizador...

ShunyaNet-Sentinel

ShunyaNet Sentinel UPDATED: 03/02/2026 ShunyaNet Sentinel is a lightweight, cyberpunk-themed program that ingests RSS feeds e.g., breaking news, social media, sends them to an LLM for analysis, and delivers alerts and summary reports directly to the GUI and Slack at regular intervals. The project...

IfritProxy

🔥 AI-Powered Threat Deception & Intelligence Platform Turn attackers into intelligence sources with adaptive honeypot responses 📦 Quick Start • ✨ Features • 🔄 How It Works • 📚 Docs • 🔌 API Brought to the community by 🎯 What is IFRIT? IFRIT is an intelligent reverse proxy that sits between the...

zdr

Zero Data Retention ZDR for LLM Providers Last updated: April 2026 A practical guide to keeping your data private when using LLM APIs. Covers zero-retention endpoints, self-hosting, compliance requirements, and data protection patterns for engineers in regulated industries. Table of Contents Whic...

redthread

RedThread 취약점을 찾으세요. 판정하세요. 수정안을 작성하세요. 무엇이 바뀌었는지 증명하세요. RedThread는 LLM 시스템을 테스트하고, 실패를 검증하며, 확인된 취약점을 증거 기반 방어 후보로 전환하는 CLI 우선 프레임워크입니다. 일회성 제일브레이크 데모 그 이상이 필요한 팀을 위해 만들어졌습니다. RedThread 캠페인은 공격을 실행하고, 결과를 채점하며, 후보 가드레일을 합성하고, 증거를 재생하며, 프로모션 경계를 명시적으로 유지합니다. 현재 상태: 활발한 연구 및 엔지니어링 프로젝트입니다. 이 시스템은 ...