PT-2025-21555 · WordPress · Ai Chatbot

Name of the Vulnerable Software and Affected Versions: AI ChatBot for WordPress versions prior to 6.2.4 Description: The issue concerns the AI ChatBot for WordPress plugin, which does not properly sanitize and escape some of its settings. This could allow high-privilege users, such as...

CVE-2025-47777 5ire Client Vulnerable to Cross-Site Scripting (XSS) and Remote Code Execution (RCE)

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Versions prior to 0.11.1 are vulnerable to stored cross-site scripting in chatbot responses due to insufficient sanitization. This, in turn, can lead to Remote Code Execution RCE via unsafe...

GenAI Security: Outsmarting the Bots with a Proactive Testing Framework

The increasing sophistication and integration of Generative AI GenAI models into diverse applications introduce new security challenges that traditional methods struggle to address. This research explores the critical need for proactive security measures to mitigate the risks associated with...

Google Is Using On-Device AI to Spot Scam Texts and Investment Fraud

Android’s “Scam Detection” protection in Google Messages will now be able to flag even more types of digital fraud...

Deepfake Defense in the Age of AI

The cybersecurity landscape has been dramatically reshaped by the advent of generative AI. Attackers now leverage large language models LLMs to impersonate trusted individuals and automate these social engineering tactics at scale. Let's review the status of these rising attacks, what's fueling...

On the Interplay of Explainability, Privacy and Predictive Performance with Explanation-Assisted Model Extraction

Machine Learning as a Service MLaaS has gained important attraction as a means for deploying powerful predictive models, offering ease of use that enables organizations to leverage advanced analytics without substantial investments in specialized infrastructure or expertise. However, MLaaS...

This Week in Spring - May 13th, 2025

Hi, Spring fans! As I write this, I'm at the amazing Code Remix event in Miami well, technically Tampa, Florida. I'll also be speaking at the Tampa JUG while I'm there, so look out! After that, I'll be headed back to Europe—a wee bit further north this time—to Stockholm for the amazing JForum...

Trend Micro Puts a Spotlight on AI at Pwn2Own Berlin

Get a sneak peak into how Trend Micro's Pwn2Own Berlin 2025 is breaking new ground, focusing on AI infrastructure and finding the bugs to proactively safeguard the future of computing...

A week in security (May 4 – May 10)

Last week on Malwarebytes Labs: The AI chatbot cop squad is here Lock and Code S06E09 Android fixes 47 vulnerabilities, including one zero-day. Update as soon as you can! "Your privacy is a promise we don’t break": Dating app Raw exposes sensitive user data FBI issues warning as scammers target...

Deepfakes, Scams, and the Age of Paranoia

As AI-driven fraud becomes increasingly common, more people feel the need to verify every interaction they have online...

Fake AI Tools Used to Spread Noodlophile Malware, Targeting 62,000+ via Facebook Lures

Threat actors have been observed leveraging fake artificial intelligence AI-powered tools as a lure to entice users into downloading an information stealer malware dubbed Noodlophile. "Instead of relying on traditional phishing or cracked software sites, they build convincing AI-themed platforms ...

Mattermost has an unspecified vulnerability

Mattermost is an open source collaboration platform from Mattermost, Inc. in the United States. Mattermost has a security vulnerability that stems from the Wrangler plugin that can bypass AI access control. No details of the vulnerability are provided at this time...

Private LoRA Fine-Tuning of Open-Source LLMs with Homomorphic Encryption

Preserving data confidentiality during the fine-tuning of open-source Large Language Models LLMs is crucial for sensitive applications. This work introduces an interactive protocol adapting the Low-Rank Adaptation LoRA technique for private fine-tuning. Homomorphic Encryption HE protects the...

RedTeamLLM: an Agentic AI Framework for Offensive Security

From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leverag...

ICE’s Deportation Airline Hack Reveals Man ‘Disappeared’ to El Salvador

Plus: A DOGE operative’s laptop reportedly gets infected with malware, Grok AI is used to “undress” women on X, a school software company’s ransomware nightmare returns, and more...

Google Chrome will use AI to block tech support scam websites

Google has expressed plans to use Artificial Intelligence AI to stop tech support scams in Chrome. With the launch of Chrome version 137, Google plans to use the on-device Gemini Nano large language model LLM to recognize and block tech support scams. Users already have the ability to chose...

CVE-2025-47470

Cross-Site Request Forgery CSRF vulnerability in senols GPT3 AI Content Writer gpt3-ai-content-generator allows Cross Site Request Forgery.This issue affects GPT3 AI Content Writer: from n/a through = 1.9.14...

Deploying AI Agents? Learn to Secure Them Before Hackers Strike Your Business

AI agents are changing the way businesses work. They can answer questions, automate tasks, and create better user experiences. But with this power comes new risks — like data leaks, identity theft, and malicious misuse. If your company is exploring or already using AI agents, you need to ask: Are...

Security Bulletin: IBM Maximo Application Suite Ai-Service Component uses A vulnerability classified as problematic has been found in PyTorch 2.6.0. Affected is the function torch.jit.jit_module_from_flatbuffer.

Summary Security Bulletin: IBM Maximo Application Suite Ai-Service Component uses A vulnerability classified as problematic has been found in PyTorch 2.6.0. Affected is the function torch.jit.jitmodulefromflatbuffer.This bulletin contains information regarding the vulnerability and its fixture...

Google Rolls Out On-Device AI Protections to Detect Scams in Chrome and Android

Google on Thursday announced it's rolling out new artificial intelligence AI-powered countermeasures to combat scams across Chrome, Search, and Android. The tech giant said it will begin using Gemini Nano, its on-device large language model LLM, to improve Safe Browsing in Chrome 137 on desktops...