OpenAI Launches GPT-5.6-Cyber with Reduced Safeguards for Exploit Development

OpenAI on Monday unveiled a new cybersecurity-focused model called GPT‑5.6‑Cyber that it said is focused on vulnerability research, penetration testing, and incident response. "Built on GPT‑5.6 Sol, it is trained to improve capabilities on several specialized cybersecurity tasks e.g., finding...

CVE-2026-63520: Microsoft SharePoint Remote Code Execution (FIXED)

Overview Rapid7 Labs conducted a zero-day research project against Microsoft SharePoint, resulting in the discovery of two new vulnerabilities that, when chained together, achieve unauthenticated remote code execution RCE against a vulnerable SharePoint server. Today, both Rapid7 and Microsoft ar...

Metabase-Exploit

Metabase SQL Injection Zero-Day Exploit GHSA-vwf4-m7j8-wcjf...

Pass-The-Passkey Family of Attacks

Research on passkey security uncovered three practically exploitable zero-day vulnerabilities in Windows 11 and Microsoft Entra ID. Two of them form a replay chain: Windows writes complete WebAuthn assertions to the event log for device-bound and hybrid authenticators, while Microsoft Entra ID...

Nightmare-Windows-0-day-exp

Windows Zero-Day Exploit Collection !Research Use Onlyhtt...

Metabase Zero-Day Exploited in Wild Allows Admin Access Without Authentication

Metabase has warned that a maximum-severity security flaw impacting its business intelligence and data visualization software package has been exploited in the wild as a zero-day. The vulnerability CVSS score: 10.0, which does not carry a CVE identifier, allows an unauthenticated remote attacker ...

N-able Issues N-central Hotfix 2 as Attackers Reach Managed Systems and Persist

N-able has released a fresh round of hotfixes for N‑central as part of its investigation into ongoing exploitation of a recently disclosed security flaw in the Remote Monitoring and Management RMM product. "We are proactively expanding protections in response to ongoing monitoring of threat actor...

From Documentation to Zero-Day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers

Existing fuzzers for PDF readers rely on simple test cases that involve only individual API calls, leading to limited coverage and potentially missing vulnerabilities that require sequences of API calls. To address these limitations, we propose PDFuzzer, a novel PDF engine fuzzer that automatical...

MDEV-40470

MDEV-40470 — MariaDB 0day: GRANT PROXY privilege escalation +...

Important: 7zip

Issue Overview: NOTE: Since p7zip/16.02+transitional.1 src:p7zip is only an empty source package NOTE: depending on 7zip. Mark this version as fixed version. NOTE: https://www.zerodayinitiative.com/advisories/ZDI-26-444/ DEBIANBUG: 1142293 CVE-2026-14266 Affected Packages: 7zip Issue Correction:...

More on the OpenAI Agent’s Attack on Hugging Face

Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own...

INC Ransomware Emerges as Dominant Actor Exploiting SonicWall SMA 1000 Flaws

The INC Ransomware operation has emerged as the "dominant threat actor" exploiting the recently disclosed security flaws in SonicWall Secure Mobile Access SMA 1000 series VPN appliances. In a report published over the weekend, Resecurity said it observed the INC Ransomware accelerating its activi...

Zero-Day Remediation Meets Operational Resiliency

Executive Summary In the Frontier AI era, the number of CISA-known exploited vulnerabilities has increased by 6.5x over the past four years, and time-to-exploitation has collapsed to -7 days. Traditional monthly patch cycles cannot keep up. Organizations need a new operating model that detects at...

vet v1.18.1

Quick Start • Documentation • Community !NOTE vet supports special mode for Agent Skills. Run vet scan --agent-skill to scan an Agent Skill hosted in a GitHub repository. Why vet? 70-90% of modern software is open source code — how do you know it's safe? Traditional SCA tools drown you in CVE...

CVE-2026-5057

ATEN Unizon RpcProvider Missing Authentication Denial-of-Service Vulnerability. This vulnerability allows remote attackers to create a denial-of-service condition on affected installations of ATEN Unizon. Authentication is not required to exploit this vulnerability. The specific flaw exists withi...

OpenAI explains how its AI agent breached Hugging Face

On July 28, OpenAI published an update on the agent that escaped its sandbox and hacked into Hugging Face during an internal cybersecurity evaluation. In the update, OpenAI reiterates that the “rogue” system was a more capable, pre‑release research model, not something intended for public...

Public PoC Released for Exploited Check Point SmartConsole Authentication Bypass

Cybersecurity researchers have shared additional technical details about a recently patched critical security flaw impacting Check Point Security Management Server and Multi-Domain Security Management Server MDS that has come under active exploitation in the wild. The vulnerability, tracked as...

JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach

JFrog has confirmed that OpenAI models exploited a zero-day in self-hosted Artifactory while trying to reach the open internet from a sealed evaluation environment. Artifactory is JFrog's software repository manager. OpenAI says the models then escalated privileges and moved laterally until they...

Lessons from the OpenAI and Hugging Face Incident: When Safety Filters Disarm the Defender

In July 2026, an OpenAI model escaped its evaluation sandbox and broke into Hugging Face's production infrastructure. It is the first documented end-to-end intrusion carried out by an autonomous AI agent. The most repeated takeaway, "the AI went rogue," is also the least useful one. The real...

OpenAI’s agent escaped its sandbox during a security test

During an internal OpenAI security evaluation, a chain of AI models escaped its sandbox, reached the internet, and then accessed Hugging Face infrastructure to complete the test objective. OpenAI is a leading artificial intelligence AI research and deployment company. Its best-known product is...