pentestagent

PentestAgent AI Penetration Testing https://github.com/user-attachments/assets/a67db2b5-672a-43df-b709-149c8eaee975 Requirements Python 3.10+ API key for OpenAI, Anthropic, or other LiteLLM-supported provider Install root@kitploit: Clone git clone https://github.com/GH05TCREW/pentestagent.git cd...

defending-code-reference-harness

Defending Code Reference Harness A reference implementation for autonomous vulnerability discovery and remediation with Claude, based on our learnings from partnering with security teams at several organizations since launching Claude Mythos Preview. For a write up of these learnings along with...

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...

saffron

Saffron-1: Inference Scaling for LLM Safety Assurance 📖 Paper 🛠️ Dependencies The code was tested under the following dependencies: Python 3.12.3 CUDA 12.2 typingextensions==4.14.0 numpy==2.2.6 torch==2.5.1 huggingfacehub==0.30.2 accelerate==1.1.1 datasets==3.1.0 evaluate==0.4.3...

SWE-agent

!warning Most of our current development effort is on mini-swe-agent, which has superseded SWE-agent. It matches the performance performance of SWE-agent, while being much simpler. See the FAQ for more details about the differences. Our general recommendation is to use mini-SWE-agent instead of...

galah

TL;DR: Galah /ɡəˈlɑː/ - pronounced ‘guh-laa’ is an LLM-powered web honeypot designed to mimic various applications and dynamically respond to arbitrary HTTP requests. Galah supports major LLM providers, including OpenAI, GoogleAI, GCP's Vertex AI, Anthropic, Cohere, and Ollama. Unlike traditional...

exfil-scan

exfil-scan Scan LLM outputs and AI-generated content for data exfiltration signals before they reach users, logs, or downstream systems. 1 Why exfil-scan exists Modern LLM applications routinely process sensitive prompts, internal documents, API responses, and user data. That creates a new securi...

llm-censorship-steering

LLM Censorship Steering This repository contains code implementation for Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control by Hannah Cyberey and David Evans. We introduce a method that finds "steering vectors" from LLM internals for detecting and controlling the...

IF-Guide

IF-Guide: Influence Function-Guided Detoxification of LLMs NeurIPS 2025 This repository contains the code for IF-Guide, the LLM detoxification technique introduced in our paper: IF-Guide: Influence Function-Guided Detoxification of LLMs Zachary Coalson , Juhan Bae, Nicholas Carlini, Sanghyun Hong...

cve-bench

CVE-Bench A benchmark for evaluating LLM agents on fixing real-world security vulnerabilities. Agents run inside sandboxed Docker containers and are scored against the maintainer's security test suite. Requirements Python 3.12+ Docker OPENAIAPIKEY, ANTHROPICAPIKEY, and/or POOLSIDEAPIKEY in your...

MalEval

MalEval Article: Is “Knowing It’s Malicious” Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing Article DOI: 10.1145/3832187 MalEval is a framework for evaluating Android malware behavior reports generated by large language models. The code in this repository implements two...

mulot

mulot -4285F4?logo=googlechrome&logoColor=white Agentic AI web pentester that drives a browser. An open-weights LLM GLM-5.2, Gemma or Qwen drives a real headless Chromium through a Burp-style toolkit and works a target the way a human pentester would. No frontier model, no agent running inside a...

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...

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...

VulnFanatic-NG

VulnFanatic-NG LLM-assisted vulnerability research for Binary Ninja. VulnFanatic-NG adds a sidebar panel that scans the current binary and asks an LLM — a locally hosted OpenAI-compatible model by default, or Anthropic Claude, Google Gemini, or Azure OpenAI see LLM backends — to judge whether...

pike-agent

Pike Agent pike-agent records and analyzes how programs behave on Linux. It traces a program's activity, indexes it into a database, and lets you chat with an LLM agent about it in a TUI. Example of prompts: Crash diagnosis: This program crashed with a bus error. What happened? Race condition...

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...

vuln-scanner

vuln-scanner An automated vulnerability assessment platform that orchestrates 86 open-source security tools , aggregates and deduplicates findings, runs an optional OpenAI-compatible LLM analysis layer for triage, clustering, and remediation, generates proof-of-concept scripts , and produces...

honeyprompt

honeyprompt Presentamos honeyprompt, un framework de decepción basado en LLM creado por/para desarrolladores web. El proyecto personal de @alectrocute. Compatible con todos los principales proveedores de LLM en la nube y locales. SSH, HTTP, TLS, TCP, telnet y más. Se distribuye como un contenedor...

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...