Vertex AI SDK 1.131.0 Cross Site Scripting Scanner

This script is a defensive behavioral security scanner designed to test whether HTML reports generated by the internal visualization module of the google-cloud-aiplatform part of Google Cloud improperly render unescaped user-controlled input...

Important: Red Hat Security Advisory: Red Hat AI Inference Server Model Optimization Tools 3.2.2 (CUDA)

Red Hat AI Inference Server Model Optimization Tools 3.2.2 CUDA is now available. Red Hat® AI Inference Server Model Optimization Tools...

Secure agentic AI for your Frontier Transformation

Today we shared the next step to make Frontier Transformation real for customers across every industry with Wave 3 of Microsoft 365 Copilot, Microsoft Agent 365, and Microsoft 365 E7: The Frontier Suite. Introducing the First Frontier Suite built on Intelligence and Trust As our customers rapidly...

A week in security (March 2 – March 8)

Last week on Malwarebytes Labs: One click on this fake Google Meet update can give attackers control of your PC Beware of fake OpenClaw installers, even if Bing points you to GitHub Fake CleanMyMac site installs SHub Stealer and backdoors crypto wallets Windows File Shredder: When deleting a file...

EUVD-2026-10279

A vulnerability was detected in Bytedesk up to 1.3.9. Affected is the function getModels of the file source-code/src/main/java/com/bytedesk/ai/springai/providers/gitee/SpringAIGiteeRestService.java of the component SpringAIGiteeRestController. Performing a manipulation of the argument apiUrl...

This Week in Spring - March 9th, 2026

Hi Spring fans! Welcome to another rip-roaring installment of This Week in Spring! I'm writing this in an Uber en route to the airport to get to awsome Atlanta, GA, for Devnexus 2026! Who's goin'? You goin'? We - the Spring team - will be there in force! Come say hi at the boothes or come see our...

Bytedesk 代码问题漏洞

Bytedesk is a multi-channel intelligent customer service platform developed by the individual developers of bytedesk.com. Versions of Bytedesk 1.3.9 and earlier contained code vulnerabilities. These vulnerabilities stemmed from incorrect handling of the parameter apiUrl in the file...

Security Considerations for Multi-Agent Systems

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct security vulnerabilities from those documented for singular AI...

Cybersecurity AI: Hacking Consumer Robots in the AI Era

Is robot cybersecurity broken by AI? Consumer robots -- from autonomous lawnmowers to powered exoskeletons and window cleaners -- are rapidly entering homes and workplaces, yet their security remains rooted in assumptions of specialized attacker expertise. This paper presents evidence that...

CVE-2026-3789

CVE-2026-3789 affects Bytedesk up to version 1.3.9, specifically the getModels function in SpringAIGiteeRestService.java within SpringAIGiteeRestController. The vulnerability arises from manipulating the apiUrl argument, leading to server-side request forgery and remote exploitation. An exploit i...

CVE-2026-3788 Bytedesk SpringAIOpenrouterRestController SpringAIOpenrouterRestService.java getModels server-side request forgery

A security vulnerability has been detected in Bytedesk up to 1.3.9. This impacts the function getModels of the file source-code/src/main/java/com/bytedesk/ai/springai/providers/openrouter/SpringAIOpenrouterRestService.java of the component SpringAIOpenrouterRestController. Such manipulation of th...

claude-bug-bounty

Claude Bug Bounty Hunter The AI-native bug bounty framework...

CVE-2026-1981

The HUMN-1 AI Website Scanner & Human Certification by Winston AI plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the winstondisconnect function in all versions up to, and including, 0.0.3. This makes it possible for authenticated...

WordPress plugin HUMN-1 AI Website Scanner & Human Certification by Winston AI 安全漏洞

WordPress and WordPress plugins are both products of the WordPress Foundation. WordPress is a blog platform developed using the PHP language. This platform allows for the creation of personal blog websites on servers based on PHP and MySQL. A WordPress plugin is an application that can be install...

CVE-2026-1981 Winston AI <= 0.0.3 - Missing Authorization to Authenticated (Subscriber+) Arbitrary Plugin Settings Deletion

The HUMN-1 AI Website Scanner & Human Certification by Winston AI plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the winstondisconnect function in all versions up to, and including, 0.0.3. This makes it possible for authenticated...

CVE-2026-1981

The HUMN-1 AI Website Scanner & Human Certification by Winston AI plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the winstondisconnect function in all versions up to, and including, 0.0.3. This makes it possible for authenticated...

How to scan for vulnerabilities with GitHub Security Lab’s open source AI-powered framework

For the last few months, we've been using the GitHub Security Lab Taskflow Agent along with a new set of auditing taskflows that specialize in finding web security vulnerabilities. They also turn out to be very successful at finding high-impact vulnerabilities in open source projects. As security...

GHSA-87FH-RC96-6FR6

creationtimestamp| type| source ---|---|--- 2026-03-06 20:09:04+00:00| seen| https://github.blog/security/how-to-scan-for-vulnerabilities-with-github-security-labs-open-source-ai-powered-framework/...

CVE-2026-23802

Unrestricted Upload of File with Dangerous Type vulnerability in Jordy Meow AI Engine ai-engine allows Using Malicious Files.This issue affects AI Engine: from n/a through = 3.3.2...

EUVD-2026-9988

OpenSift is an AI study tool that sifts through large datasets using semantic search and generative AI. Prior to version 1.6.3-alpha, the URL ingest pipeline accepted user-controlled remote URLs with incomplete destination restrictions. Although private/local host checks existed, missing...