Exploit for Exposure of Sensitive Information to an Unauthorized Actor in Microsoft

CVE-2026-33829 - Security Vulnerability Quick Usage ba...

ExploitBench AI Exploit Benchmark Tool

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution...

CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-To-End Cybersecurity Capabilities

AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. However, existing cybersecurity evaluations of AI systems are limited in scale or scope, and fail to capture the end-to-end lifecycle of real-world...

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish. We introduce a quality-diversity evolutionary framework that operates at the...

NeuroLog: Reasoning You Can Audit -- Neuro-Symbolic Vulnerability Discovery Via LLM Facts, Datalog, and SMT

Vulnerability discovery on C/C++ source asks the analyst to choose between heavyweight static analysers, which need a working build before a single query runs, and free-form LLMs, which read source readily but invent details and lose track of cross-function dataflow on real codebases. We present...

project_hydra

Project HYDRA Automated vulnerability discovery & exploitat...

The AI Era Is Creating a Bug-Hunting Arms Race

As attackers ramp up their AI exploit development, the search for software vulnerabilities is changing rapidly...

Claude Mythos AI Finds 10,000 High-Severity Flaws in Widely Used Software

Anthropic on Friday disclosed that Project Glasswing has helped uncover more than 10,000 high- or critical-severity vulnerabilities across some of the most "systemically" important software across the world since the cybersecurity initiative went live last month. Project Glasswing is a defensive...

WordPress All in One SEO – Powerful SEO Plugin to Boost SEO Rankings & Increase Traffic plugin <= 4.9.7 - Authenticated (Contributor+) Sensitive Information Exposure vulnerability

Authenticated Contributor+ Sensitive Information Exposure vulnerability discovered by 0x61626390 in WordPress Plugin All In One SEO Pack versions = 4.9.7...

WordPress Games Catalog plugin <= 1.2.0 - Cross-Site Request Forgery to Arbitrary Game/Post Deletion vulnerability

Cross-Site Request Forgery to Arbitrary Game/Post Deletion vulnerability discovered by Muhammad Nur Ibnu Hubab Ibnu - Pondok Teknologi in WordPress Plugin Games Catalog versions = 1.2.0...

WordPress Bigfishgames Syndicate plugin <= 1.2 - Cross-Site Request Forgery to Settings Reset and Update vulnerability

Cross-Site Request Forgery to Settings Reset and Update vulnerability discovered by Muhammad Nur Ibnu Hubab Ibnu - Pondok Teknologi in WordPress Plugin Bigfishgames Syndicate versions = 1.2...

shadow-pentest

🖤 Shadow Pentest Framework v1.0 Automated CVE Discovery & E...

WordPress FOX – Currency Switcher Professional for WooCommerce plugin <= 1.4.5 - Missing Authorization to Authenticated (Contributor+) Configuration Deletion vulnerability

Missing Authorization to Authenticated Contributor+ Configuration Deletion vulnerability discovered by Ren Voza in WordPress Plugin FOX versions = 1.4.5...

Microsoft's MDASH AI System Finds 16 Windows Flaws Fixed in Patch Tuesday

Microsoft has unveiled a new multi-model artificial intelligence AI-driven system called MDASH to facilitate vulnerability discovery and remediation at scale, adding that it's being tested by some customers as part of a limited private preview. MDASH, short for m ulti-mod el a gentic s canning h...

Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark

In this article 1. AI-powered vulnerability discovery at hyper-scale 2. Codename: MDASH—Microsoft Security’s new multi-model agentic scanning harness 3. Using codename MDASH for security research 4. The 5.12.2026 Patch Tuesday cohort 5. Two deep dives 1. CVE-2026-33827—Remote unauthenticated UAF ...

Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark

In this article 1. AI-powered vulnerability discovery at hyper-scale 2. Codename: MDASH—Microsoft Security’s new multi-model agentic scanning harness 3. Using codename MDASH for security research 4. The 5.12.2026 Patch Tuesday cohort 5. Two deep dives 1. CVE-2026-33827—Remote unauthenticated UAF ...

WordPress ProfileGrid – User Profiles, Groups and Communities plugin <= 5.9.8.4 - Missing Authorization to Authenticated (Subscriber+) Group Settings Modification vulnerability

Missing Authorization to Authenticated Subscriber+ Group Settings Modification vulnerability discovered by Chawabhon Netisingha JNX03 in WordPress Plugin ProfileGrid versions = 5.9.8.4...

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code...

PwnedAgent

PwnedAgent...

Position: AI Security Policy Should Target Systems, Not Models

We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, parallel exploration, and evolutionary optimization. Together, our results demonstrate that both safety bypass of frontier models and software...