pFuzz

pFuzz 是什么 / pFuzz Nedir ❓ pFuzz 是我们为研究而开发的一种高级红队模糊测试工具。它帮助我们通过同时使用不同的方法来绕过 Web 应用防火墙。 pFuzz 是我们为 Web 应用研究而开发的高级模糊测试工具。它旨在加速在不同安全应用上尝试各种攻击方法的过程。 描述 EN pFuzz 是一种用 Python 语言开发的工具，旨在为 Web 应用研究提供高级模糊测试能力。由于该应用具有模块化结构，它能够快速将新发现/待发现的 WAF 绕过方法添加到 pFuzz 中，并在所有其他 WAF...

nishang

Nishang Nishang es un conjunto de scripts y payloads que permite el uso de PowerShell para seguridad ofensiva, pruebas de penetración y red teaming. Nishang es útil durante todas las fases de las pruebas de penetración. Por Nikhil Mittal Fundador de Altered Security - ¡Formación práctica en red...

redshell

RedShell An interactive command prompt for red teaming and pentesting. Automatically pushes commands through SOCKS4/5 proxies via proxychains. Optional Cobalt Strike integration pulls beacon SOCKS4/5 proxies from the team server. Automatically logs activities to a local CSV file and a Cobalt Stri...

pwndrop

pwndrop is a self-deployable file hosting service for sending out red teaming payloads or securely sharing your private files over HTTP and WebDAV. If you've ever needed to quickly set up an nginx/apache web server to host your files and you were never happy with the limitations of python -m...

siras

SIRAS v3.0 is a modern Security Incident Response Automated Simulation framework designed to manage red teaming exercises as code. You can execute controlled security simulations that test your Incident Response plan in realistic scenarios. The main goal of SIRAS is to provide red teaming exercis...

macro_pack

macropack Descripción breve Advertencia: MacroPack no se mantiene desde 2021, si eres un profesional y necesitas herramientas ofensivas de infosec para acceso inicial, asunción de brecha, evasión de EDR, revisa https://www.balliskit.com MacroPack Community es una herramienta utilizada para...

electroniz3r

electroniz3r Toma el control de los permisos de TCC de las aplicaciones Electron de macOS con electroniz3r. La herramienta se presentó por primera vez en DEFCON31 en Las Vegas durante mi charla ELECTRONizing macOS privacy - a new weapon in your red teaming armory. Descripción general root@kitploi...

LLM-MCP-Security-Field-Guide

🛡️ AI 安全领域指南 — LLM + MCP 安全 面向 LLM 应用和模型上下文协议（MCP）部署的最全面、最新、以实践者为中心的安全参考。 涵盖真实 CVE、实时攻击模式、OWASP 框架、红队工具和可操作检查清单 — 每周更新。 为何需要本指南 AI 安全格局在 2025–2026 年间发生了剧变： 🔴 492 个 MCP 服务器 公开暴露且无身份认证（Trend Micro，2026） 🔴 CVE-2025-6514 通过 mcp-remote OAuth 代理危及 437,000+ 个开发者环境 🔴 在 ClawHub 代理注册表中确认了 1,184 个恶意技能 （Antiy...

gemini-2.5-pro-nf-tables-red-teaming

Gemini 2.5 Pro nftables Red Teaming Case Study CVE-2023-32233 LLM Safety Research | Responsible Disclosure | AI Alignment Evaluation Researcher : Niranj R Mahaswar Destawell Google AI Vulnerability Reward Program : 889286 — Out of Scope Summary This repository documents a comparative LLM red...

gemini-2.5-pro-nf-tables-red-teamin

gemini-2.5-pro-nf-tables-red-teamin A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution regarding legacy Linux kernel vulnerability primitives CVE-2023-32233. Link to case study website :...

Beginners-Guide-to-Obfuscation

Evading Detection: A Beginner's Guide to Obfuscation Defenders are constantly adapting their security to counter new threats. Our mission is to identify how they plan on securing their systems and avoid being identified as a threat. This is a hands-on class to learn the methodology behind malware...

promptfoo v0.122.1

Promptfoo: LLM evals & red teaming promptfoo is a CLI and library for evaluating and red-teaming LLM apps. Stop the trial-and-error approach - start shipping secure, reliable AI apps. Website · Getting Started · Red Teaming · Documentation · Discord Promptfoo is now part of OpenAI. Promptfoo...

OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol

OpenAI has disclosed details of GPT-Red , an internal automated red-teaming model that scales prompt injection vulnerability discovery with an aim to fix issues before the tools are deployed widely. "GPT‑Red is a strong red-teamer, and our previous models are highly vulnerable to its prompt...

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Hierarchical multi-agent systems MAS are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particular...

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Large Language Models LLMs are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at...

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

RedEdit: Agentic Red-Teaming of Image Safety Classifiers Via MCTS-Guided Photo-Editing

Image safety classifiers serve as a critical component of contemporary content moderation systems on the internet. However, their resilience against user-style malicious image editing remains underexplored. Such behaviors are highly prevalent in daily scenarios but difficult to fully reproduce. T...

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

Recent computer-using-agent CUA red-teaming papers report prompt-injection attack success rates ASR of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel. We ask whether those techniques, reproduced as hand-crafted templates, still...

-cascade-scan

cascade-scan AI Agent security evaluation framework — autom...

ADR: An Agentic Detection System for Enterprise Agentic AI Security

We present the Agentic AI Detection and Response ADR system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol MCP. We identify three persistent challenges in this domain: 1 limited observability -- existing Endpoint...