Agentic Fuzzing: Opportunities and Challenges

Fuzzers and static analyzers find many bugs but struggle with logic bugs in mature codebases. Triggering such a bug often requires multi-step reasoning that produces no distinctive execution feedback, and variants can appear across implementations too different for a single pattern to match. Rece...

Root-Cause-Driven Automated Vulnerability Repair

Recent LLM-based systems have made automated vulnerability repair increasingly practical, but two challenges remain. First, without strong signals about where a bug originates, repair agents drift toward shallow edits that silence the observed failure while leaving the underlying defect unresolve...

cve-deep-dive

Report Bug · Request Feature Table of Contents a...

Beyond Code Reasoning: A Specification-Anchored Audit Framework for Expert-Augmented Security Verification

Security-critical software is routinely audited by tools that reason about vulnerabilities as repository-local code patterns. Yet specification-governed systems -- protocol stacks, consensus implementations, cryptographic libraries -- are constrained by invariants and correctness conditions defin...

Can SOC Operators Explain Their Decisions While Triaging Alarms? A Real-World Study

Security Operations Centers SOCs are pivotal in modern enterprises. Tasked to monitor complex network environments constantly under attack, SOCs can be active 24/7 and can include hundreds of operators supported by state-of-the-art technologies. Abundant research has studied the internal processe...

cyber-punk

Cyber Punk Security Vulnerability Scanner A Claude Code plu...

Exploit for CVE-2020-1938

CVE-2020-1938 Tomcat AJP Ghostcat Analysis This repository co...

CVE-2026-32121

OpenEMR is a free and open source electronic health records and medical practice management application. Prior to 8.0.0.1, Stored XSS in prescription CSS/HTML print view via patient demographics. That finding involves server-side rendering of patient names via raw PHP echo. This finding involves...

PT-2026-24376

Name of the Vulnerable Software and Affected Versions Microsoft Authenticator affected versions not specified Description A condition exists where an unauthorized attacker can disclose information locally. The issue relates to Cwe not being in rca categories. Recommendations At the moment, there ...

Inside the Fix: Analysis of In-the-Wild Exploit of CVE-2026-21513

Read how PatchDiff-AI uncovered the root cause of CVE-2026-21513 — an actively exploited MSHTML vulnerability — and how APT28 leveraged it in real-world attacks...

From Detection to Remediation: It’s Time to Rethink AppSec Around Exploitability and Root Cause Fixes

Learn how Wiz is fundamentally changing AppSec by using the Security Graph to connect validated runtime vulnerabilities directly back to source code. Stop chasing alerts and fix what’s truly exploitable...

Exploit for CVE-2025-12197

Security Research This repository contains my security resea...

Reducing Cloud Chaos: Rapid7 Partners with ARMO to Deliver Cloud Runtime Security

Rapid7 has partnered with ARMO, a leader in cloud infrastructure and application security based on runtime data, to offer Cloud Runtime Security. The new offering, currently in beta, extends our vulnerability and exposure management solution, Exposure Command, into the moment where cloud risk...

Patch Wednesday: Root Cause Analysis with LLMs

...

Inside the Fix: AI-Powered Root Cause Analysis of CVE-2025-60719

...

Google's New AI Doesn't Just Find Vulnerabilities — It Rewrites Code to Patch Them

Google's DeepMind division on Monday announced an artificial intelligence AI-powered agent called CodeMender that automatically detects, patches, and rewrites vulnerable code to prevent future exploits. The efforts add to the company's ongoing efforts to improve AI-powered vulnerability discovery...

EUVD-2022-24733

Malicious code in bioql PyPI...

EUVD-2025-16335

Malicious code in bioql PyPI...

EUVD-2024-26774

Malicious code in bioql PyPI...

LLM-Based Vulnerability Discovery through the Lens of Code Metrics

Large language models LLMs excel in many tasks of software engineering, yet progress in leveraging them for vulnerability discovery has stalled in recent years. To understand this phenomenon, we investigate LLMs through the lens of classic code metrics. Surprisingly, we find that a classifier...