The vulnerability of the SROOT component in NVIDIA DGX OS workstations for artificial intelligence DGX Spark allows a intruder to gain unauthorized access to protected information.

The vulnerability of the SROOT component in NVIDIA DGX OS workstations for AI systems, such as DGX Spark, is related to errors in boundary removal of critical data. Exploiting this vulnerability can allow attackers to gain unauthorized access to protected information...

Exploit for CVE-2023-1234

🤖 XBOW-Metascan: AI-Powered Autonomous Pentesting Platform !...

CVE-2025-13381

CVE-2025-13381 (AYS & WordPress) Vulnerability exists in the AI ChatBot with ChatGPT and Content Generator by AYS plugin for WordPress due to a missing capability check in the ays_chatgpt_save_wp_media function through version 2.7.0, enabling unauthenticated users to upload media files. Wordfence...

PT-2025-48254

The AI ChatBot with ChatGPT and Content Generator by AYS plugin for WordPress is vulnerable to unauthorized access due to a missing capability check on the 'ays chatgpt save wp media' function in all versions up to, and including, 2.7.0. This makes it possible for unauthenticated attackers to...

AI Inference at the Edge: How Akamai’s Evolution Made It Possible

Read how Akamai, a pioneer in CDNs, is undergoing a profound strategic transformation into a diversified cloud and cybersecurity provider in the AI era...

A Safety and Security Framework for Real-World Agentic Systems

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising from the dynamic interactions among models, orchestrator...

Can We Trust AI with Our Cybersecurity? The Growing Importance of AI Security

Artificial intelligence AI helps us in doing small and big things that are important in our daily lives.…...

BrowseSafe: Understanding and Preventing Prompt Injection within AI Browser Agents

The integration of artificial intelligence AI agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web agents, yet the resulting impact within real-world environments...

From One Attack Domain to Another: Contrastive Transfer Learning with Siamese Networks for APT Detection

Advanced Persistent Threats APT pose a major cybersecurity challenge due to their stealth, persistence, and adaptability. Traditional machine learning detectors struggle with class imbalance, high dimensional features, and scarce real world traces. They often lack transferability-performing well ...

A week in security (November 17 – November 23)

Last week on Malwarebytes Labs: AI teddy bear for kids responds with sexual content and advice about weapons Fake calendar invites are spreading. Here’s how to remove them and prevent more Budget Samsung phones shipped with unremovable spyware, say researchers What the Flock is happening with...

IBM Concert Cross-Site Scripting Vulnerability

IBM Concert is a generative artificial intelligence-driven automated application management and monitoring tool based on the watsonx platform released in May 2024 by IBM. IBM Concert suffers from a cross-site scripting vulnerability that stems from the application's lack of effective filtering an...

IBM Concert Output Neutralization Malpractice Vulnerability

IBM Concert is a generative artificial intelligence-driven automated application management and monitoring tool based on the watsonx platform released in May 2024 by IBM. IBM Concert suffers from an improper output neutralization vulnerability that can be exploited by an attacker to cause a forge...

Ares

Ultimate SQLi Tool v3.0 — FINAL The most powerful, autonomous...

PT-2025-47787

Name of the Vulnerable Software and Affected Versions S2B AI Assistant – ChatBot, ChatGPT, OpenAI, Content & Image Generator plugin for WordPress versions through 1.7.8 Description The software is susceptible to arbitrary file uploads because of a lack of file type validation within the storeFile...

GenAI: Harness the Power, Eliminate the Risk — A Practical Playbook for Securing AI from Day One

Enterprises everywhere are racing to leverage AI to gain sharper insights, automate workflows, and deliver richer customer experiences. Based on an assessment conducted by Bain & Company, generative AI adoption is soaring, with 95% of US companies using it, up 12 percentage points in just a year...

It’s not personal, it’s just business

Welcome to this week's edition of the Threat Source newsletter. This week, we explore how advances in agentic AI are rapidly transforming the cyber crime business. Agentic AI programming gives AI agents autonomy, allowing them to interact with external systems to collect information, make decisio...

[Correction] Gmail can read your emails and attachments to power “smart features”

Update November 22. We’ve updated this article after realising we contributed to a perfect storm of misunderstanding around a recent change in the wording and placement of Gmail's smart features. The settings themselves aren’t new, but the way Google recently rewrote and surfaced them led a lot o...

IBM Concert 跨站脚本漏洞

IBM Concert is a generative artificial intelligence-driven automated application management and monitoring tool based on the watsonx platform released in May 2024 by IBM. IBM Concert suffers from a cross-site scripting vulnerability that stems from the application's lack of effective filtering an...

A CMO’s Perspective: Why This Moment Matters in the AI Era

Akamai’s CMO describes how the company is radically rethinking and extending the systems needed to unlock AI's true potential...

Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...