Who'S the Evil Twin? Differential Auditing for Undesired Behavior

Detecting hidden behaviors in neural networks poses a significant challenge due to minimal prior knowledge and potential adversarial obfuscation. We explore this problem by framing detection as an adversarial game between two teams: the red team trains two similar models, one trained solely on...

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic environments, especially under attack? To investigate, we...

Exploit for CVE-2017-0144

This repository is an offensive tool for Windows. It is an implementation of the DoublePulsar backdoor in C/C++. The tool includes a suite of exploits and detectors for various vulnerabilities, including the EternalBlue vulnerability CVE-2017-0144. The tool can be used to upload a DLL to a...

Exploit for Incorrect Default Permissions in Microsoft

This List is no longer updated. Awesome Red Teaming List of Awesome Red Team / Red Teaming Resources This list is for anyone wishing to learn about Red Teaming but do not have a starting point. Anyway, this is a living resources and will update regularly with latest Adversarial Tactics and...

Vulmap

This is an online local vulnerability scanner project called Vulmap. It is an open-source tool that can be used for defensive and offensive purposes. The tool scans the localhost to gather installed software information and checks for vulnerabilities using the Vulmon API. If vulnerabilities exist...

Enabling Cyber Security Education through Digital Twins and Generative AI

Digital Twins DTs are gaining prominence in cybersecurity for their ability to replicate complex IT Information Technology, OT Operational Technology, and IoT Internet of Things infrastructures, allowing for real time monitoring, threat analysis, and system simulation. This study investigates how...

Shr3dKit

This is a Red Team Tool Kit repository, specifically designed for penetration testing and red teaming activities. The tool kit is influenced by infosecn1nja's kit and includes a wide range of tools for reconnaissance, weaponization, and delivery. The repository contains a total size of 2.5+Gb and...

Effective Red-Teaming of Policy-Adherent Agents

Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules. The challenge lies in ensuring that the agent consistently adheres to these rules and policies, appropriately refusing any request that would violate them, while...

GenBreak: Red Teaming Text-To-Image Generators Using Large Language Models

Text-to-image T2I models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation...

CVE-2025-33073

creationtimestamp| type| source ---|---|--- 2025-06-10 13:15:01+00:00| seen| https://bsky.app/profile/redteam-pentesting.de/post/3lraxxvj4ns2j 2025-06-10 13:15:02+00:00| seen| https://bsky.app/profile/redteam-pentesting.de/post/3lraxxvjaks2j 2025-06-10 15:24:53+00:00| seen|...

ScadaFlare 1.0 ScadaBR Authenticated RCE Toolkit

This is a modular post-authentication remote code execution exploit targeting ScadaBR versions prior to 1.1.0. This tool is enhanced for red team ops...

Exploit for Use of Less Trusted Source in Apache Http_Server

CVE-2022-31813 Vulnerability Checker Author: Derek Odiorn...

CVE-2025-26169

creationtimestamp| type| source ---|---|--- 2025-05-07 19:22:28+00:00| seen| https://t.me/DarkWebInformerCVEAlerts/15392 2025-05-07 22:27:10+00:00| seen| https://bsky.app/profile/cve.skyfleet.blue/post/3lomgxutklb2h 2025-05-07 22:28:48+00:00| seen|...

New whitepaper outlines the taxonomy of failure modes in AI agents

We are releasing a taxonomy of failure modes in AI agents to help security professionals and machine learning engineers think through how AI systems can fail and design them with safety and security in mind. The taxonomy continues Microsoft AI Red Team's work to lead the creation of systematizati...

New whitepaper outlines the taxonomy of failure modes in AI agents

We are releasing a taxonomy of failure modes in AI agents to help security professionals and machine learning engineers think through how AI systems can fail and design them with safety and security in mind. The taxonomy continues Microsoft AI Red Team's work to lead the creation of systematizati...

CVE-2025-3854

creationtimestamp| type| source ---|---|--- 2025-04-21 14:27:09+00:00| seen| https://infosec.exchange/users/vuldb/statuses/114376417527828395 2025-04-22 01:02:24+00:00| published-proof-of-concept| https://t.me/DarkWebInformerCVEAlerts/12775 2025-04-22 03:04:30+00:00| seen|...

Exploit for CVE-2025-2783

CVE-2025-2783 Simulated PoC for CVE-2025-2783 — a sandbox esca...

Pentales: Red Team vs. N-Day (and How We Won)

During a recent Vector Command operation, I had the chance to sit down with one of our red teamers to hear firsthand how they identified and exploited an N-Day vulnerability in a customer’s environment. It’s a clear example of how continuous red teaming can uncover and validate real-world risks...

CVE-2025-24381

creationtimestamp| type| source ---|---|--- 2025-03-28 03:27:39+00:00| seen| https://t.me/DarkWebInformerCVEAlerts/9263 2025-03-28 05:00:36+00:00| seen| Telegram/REIy8s9RHKd3lCpUQgU1ZLtNB2gCBYg9aoCqFnV7Mh0QfY 2025-03-28 05:12:10+00:00| seen| https://t.me/cvedetector/21359 2025-03-28 09:05:40+00:0...

CVE-2025-30093

creationtimestamp| type| source ---|---|--- 2025-03-27 20:50:26+00:00| seen| https://t.me/cvedetector/21334 2025-03-28 15:28:33+00:00| seen| https://t.me/DarkWebInformerCVEAlerts/9365 2025-03-28 20:49:11+00:00| seen| https://bsky.app/profile/redteamnews.bsky.social/post/3llhotwpwb52j...