TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEs

Software vulnerabilities remain one of the most persistent threats to modern digital infrastructure. While static application security testing SAST tools have long served as the first line of defense, they suffer from high false-positive rates. This article presents TitanCA, a collaborative proje...

Mythos and Cybersecurity

Last week, Anthropic pulled back the curtain on Claude Mythos Preview, an AI model so capable at finding and exploiting software vulnerabilities that the company decided it was too dangerous to release to the public. Instead, access has been restricted to roughly 50 organizations--Microsoft, Appl...

WordPress Career Section plugin <= 1.6 - Cross-Site Request Forgery to Arbitrary File Deletion vulnerability

Cross-Site Request Forgery to Arbitrary File Deletion vulnerability discovered by Ivan Cese in WordPress Plugin Career Section versions = 1.6...

vulnswarm

VulnSwarm AI-powered vulnerability discovery using multi-agen...

argus

Argus Autonomous vulnerability discovery and exploit validati...

WordPress LifterLMS plugin <= 9.2.1 - Authenticated (Custom+) SQL Injection via 'order' Parameter vulnerability

Authenticated Custom+ SQL Injection via 'order' Parameter vulnerability discovered by momopon1415 in WordPress Plugin LifterLMS versions = 9.2.1...

Why AI-Powered Vulnerability Discovery Strengthens Akamai's Security Mission

...

WordPress Micdrop theme <= 1.3.1 - PHP Object Injection vulnerability

PHP Object Injection vulnerability discovered by Denver Jackson in WordPress Theme Micdrop versions = 1.3.1...

WordPress Malmö theme <= 2.2 - Local File Inclusion vulnerability

Local File Inclusion vulnerability discovered by Tran Nguyen Bao Khanh VCI - VNPT Cyber Immunity in WordPress Theme Malmö versions = 2.2...

Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery

Symbolic execution detects vulnerabilities with precision, but applying it to large codebases requires harnesses that set up symbolic state, model dependencies, and specify assertions. Writing these harnesses has traditionally been a manual process requiring expert knowledge, which significantly...

Semantics over Syntax: Uncovering Pre-Authentication 5G Baseband Vulnerabilities

Modern 5G user equipment UE processes Radio Resource Control RRC configuration messages during early control-plane exchanges, before authentication and integrity protection are established. Prior work for testing 5G UEs has largely focused on constructing syntactically invalid inputs. In contrast...

Beamforming Feedback As a Novel Attack Surface for Wi-Fi Physical-Layer Security

With the rapid evolution of wireless technologies, Wi-Fi has expanded beyond its original role in data transmission to support various emerging applications, particularly in physical-layer security, including device authentication, user authentication, and secret key generation. Despite extensive...

Casdoor vulnerable to Open Redirect

A vulnerability was identified in Casdoor 2.356.0. Affected by this issue is some unknown functionality of the component OAuth Authorization Request Handler. Such manipulation of the argument redirecturi leads to open redirect. It is possible to launch the attack remotely. The exploit is publicly...

WordPress Oxygen theme <= 6.0.8 - Unauthenticated Server-Side Request Forgery via route_path vulnerability

Unauthenticated Server-Side Request Forgery via routepath vulnerability discovered by Ahmed Rayen Ayari in WordPress Theme Oxygen versions = 6.0.8...

security-research

Security Research & Vulnerability Proof-of-Concepts Welcome t...

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models Via Hierarchical Strategy Exploration

The rapid advancement of Vision-Language Models VLMs has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them to optimizing within a predefined strategy set and...

AI in Vulnerability Discovery: A Call for Human Oversight and Caution

...

What Boards Must Demand in the Age of AI-Automated Exploitation

“You knew, and you could have acted. Why didn’t you?” This is the question you do not want to be asked. And increasingly, it’s the question leaders are forced to answer after an incident. For years, many executive teams and boards have treated a large vulnerability backlog as an uncomfortable but...

WordPress ProfilePress plugin <= 4.16.11 - Insecure Direct Object Reference to Authenticated (Subscriber+) Arbitrary Subscription Cancellation/Expiration vulnerability

Insecure Direct Object Reference to Authenticated Subscriber+ Arbitrary Subscription Cancellation/Expiration vulnerability discovered by kai63001 in WordPress Plugin ProfilePress versions = 4.16.11...

WordPress Wolverine Framework plugin <= 1.9 - Reflected Cross Site Scripting (XSS) vulnerability

Reflected Cross Site Scripting XSS vulnerability discovered by João Pedro S Alcântara Kinorth in WordPress Plugin Wolverine Framework versions = 1.9...