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...

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...

agentic-ioc-scanner

agentic-ioc-scanner IOC scanner for agentic AI coding tools — detects Mini Shai-Hulud, Gemini CLI RCE, Cursor CVE-2026-26268, and DPRK PromptMink. A detection kit for compromise of agentic AI coding assistants Claude Code, Gemini CLI, Cursor and the dependencies they pull into your repos. Eleven...

VulnHunter

VulnHunter !NOTE A maintained fork of Capital One's VulnHunter Apache-2.0 — built to run on any agent harness , not just Claude Code. This fork's focus: harness portability , sandboxed containerized exploit validation , and measured-impact PoCs. See Why the changes · What this fork changes · The...

IPI-exposure-signal

IPI Exposure Signal This is the code repository for our paper: Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure. ArXiv version and paper link: https://arxiv.org/abs/2608.02657 This repository implements the probing pipeline for latent IPI-exposure signals:...

mcp-attack-detection-sentinel

MCP Attack Detection — Sentinel Research Lab Sentinel detection research for MCP Model Context Protocol attack patterns : unusual identity access after an MCP-related event, tool-definition mutation, cross-resource access, and possible post-exploitation behavior. The rules map to the OWASP Top 10...

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...

CVE-2025-59536

CVE-2025-59536 - the startup trust dialog implementation. Claude Vulnerability Severity: HIGH CVSS: 8.8 Impact: Confidentiality, Integrity, Availability Published: 2025-10-03 Legal For authorized security testing only. Root Cause short version Claude Code is an agentic coding tool. Versions befor...

vigolium

Vigolium - High-fidelity vulnerability scanner fusing agentic AI with native speed, modularity, and precision Vigolium provides two complementary scanning modes: Native Scan vigolium scan: Fast, powerful, and flexible. Deterministic, multi-phase scanning with 317 modules across content discovery,...

rebuff

Rebuff.ai Self-hardening prompt injection detector Rebuff is designed to protect AI applications from prompt injection PI attacks through a multi-layered defense. Playground • Discord • Features • Installation • Getting started • Self-hosting • Contributing • Docs Disclaimer Rebuff is still a...

agentic-dm-gateway

Agentic DM Gateway Security control plane for LLM agents over private chat typically Discord DMs. It sits in front of your agent. It decides who may talk, whether the session is unlocked, whether the process is paused, and whether this message is safe enough to forward. Your model and tools stay...

pyod

.. image:: https://raw.githubusercontent.com/yzhao062/pyod/master/brand/pyod-icon.svg :target: https://pyod.dev :alt: PyOD Ecosystem :width: 84px Python Outlier Detection PyOD 3 PyOD 3: Agentische Anomalieerkennung im großen Maßstab |badgewebsite| |badgepypi| |badgeanaconda| |badgedocs|...

binary-cartography

Binary Cartography Technical webinars on reverse engineering, malware analysis, and software protection. This repository hosts materials for Binary Cartography , Tim's independent webinar series on binary security. The focus is practical reverse engineering, malware analysis, and software...

ultrafuzz

Ultrafuzz Ultrafuzz is an agentic orchestrator for smart contract fuzzing and threat hunting This tool initializes a protocol repository with editable prompts and topology, runs specialized agents, collects generated fuzz tests and findings, and serves a local dashboard plus final report for...

Agentic-CLIP-Benchmark

Agentic-CLIP-Benchmark: Zero-Shot Evaluation on CIFAR-10 -green.svg This project implements a robust, automated pipeline for evaluating OpenAI's CLIP ViT-B/32 model on the full CIFAR-10 test set 10,000 images. Developed using an AI Native workflow Trae IDE , it achieves a high-precision zero-shot...

authproof-sdk

AuthProof SDK AuthProof is an audit and attribution layer for AI agents. It lets you prove what a user authorized before the agent acted, and it records what the agent actually did against that authorization. The mechanism is simple. The user signs a delegation receipt with their own private key...

3 lessons from frontier AI vulnerability research

In this article 1. Shift 1. From frontier capability to scale 2. Shift 2. From token consumption to reasoning economics 3. Shift 3. Validation and remediation as a continuous learning loop 4. Transferring security research to help open source projects 5. Open-source vulnerability reporting snapsh...

What Is Agentic Pentesting? What It Proves, and Where It Stops.

If you’re evaluating an agentic pentesting solution right now, you’ve probably heard the same pitch more than once: point it at a target, and it discovers, validates, and exploits attack paths autonomously, the way a real attacker would. That promise is worth taking seriously. It’s also worth...

NetAgent: Multi-Task Agentic Network Traffic Analysis Made Practical

Network traffic analysis is central to network security, spanning tasks from intrusion detection to encrypted traffic classification. Existing approaches either train task-specific models that generalize poorly or rely on costly traffic foundation models that still struggle under distribution...

Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement

Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces significant challenges in safety, reliability, and policy compliance. This paper presents Agentic AI based zero trust architecture Agentic-ZTA that...