Cybersecurity News

One year from now, with the release of Chrome 154 in October 2026, we will change the default settings of Chrome to enable “Always Use Secure Connections”. This means Chrome will ask for the user's permission before the first access to any public site without HTTPS. The “Always Use Secure Connections” setting warns users before accessing a site without HTTPS Chrome Security's mission is to make it safe to click on links. Part of being safe means ensuring that when a user types a URL or clicks on a link, the browser ends up where the user intended. When links don't use HTTPS, an attacker can hijack the navigation and force Chrome users to load arbitrary, attacker-controlled resources, and expose the user to malware, targeted exploitation, or social engineering attacks. Attacks like this are not hypothetical—software to hijack navigations is readily available and attackers have previously used insecure HTTP to compromise user devices in a targeted attack. Since attacker

Recently, Anthropic added the capability for Claude’s Code Interpreter to perform network requests. This is obviously very dangerous as we will see in this post. At a high level, this post is about a data exfiltration attack chain, where an adversary (either the model or third-party attacker via indirect prompt injection) can exfiltrate data the user has access to. The interesting part is that this is not via hyperlink rendering as we often see, but by leveraging the built-in Anthropic Claude APIs!

Learn how to monitor your enterprise for TOR exit node activity.

REF3927 abuses publicly disclosed ASP.NET machine keys to compromise IIS servers and deploy TOLLBOOTH SEO cloaking modules globally.

In this article, we describe how we applied survival analysis to vulnerability management (VM) data from Qualys VMDR, using the Elastic Stack.

This article describes nightMARE, a python-based library for malware researchers that was developed by Elastic Security Labs to help scale analysis. It describes how we use nightMARE to develop malware configuration extractors and carve out intelligence indicators.

The 2025 Elastic Global Threat Report provides current insights on adversary trends and defender strategies derived from real-world telemetry.

A year later: Elastic Security Labs re-examines the WARMCOOKIE backdoor.

FlipSwitch offers a fresh look at bypassing Linux kernel defenses, revealing a new technique in the ongoing battle between cyber attackers and defenders.

Key Takeaways Private Threat Briefs: 20+ private DFIR reports annually.   Contact us today for pricing or a demo!   Table of Contents: Case Summary Analysts Initial Access Execution Persistence Privilege Escalation Defense Evasion Credential Access Discovery Lateral Movement Command and Control Exfiltration Impact Timeline Diamond Model Indicators Detections MITRE ATT&CK   Case Summary The intrusion […] The post From a Single Click: How Lunar Spider Enabled a Near Two-Month Intrusion appeared first on The DFIR Report.

During the Month of AI Bugs, I described an emerging vulnerability pattern that shows how commonly agentic systems have a design flaw that allows an agent to overwrite its own configuration and security settings. This allows the agent to break out of its sandbox and escape by executing arbitrary code. My research with GitHub Copilot, AWS Kiro and a few others demonstrated how this can be exploited by an adversary with an indirect prompt injection.

Posted by Elie Bursztein and Marianna Tishchenko, Google Privacy, Safety and Security TeamEmpowering cyber defenders with AI is critical to tilting the cybersecurity balance back in their favor as they battle cybercriminals and keep users safe. To help accelerate adoption of AI for cybersecurity workflows, we partnered with Airbus at DEF CON 33 to host the GenSec Capture the Flag (CTF), dedicated to human-AI collaboration in cybersecurity. Our goal was to create a fun, interactive environment, where participants across various skill levels could explore how AI can accelerate their daily cybersecurity workflows.At GenSec CTF, nearly 500 participants successfully completed introductory challenges, with 23% of participants using AI for cybersecurity for the very first time. An overwhelming 85% of all participants found the event useful for learning how AI can be applied to security workflows. This positive feedback highlights that AI-centric CTFs can play a vital role in speeding up AI e

Elastic shares results of the 2025 AV Comparatives EPR test

This research examines how Model Context Protocol (MCP) tools expand the attack surface for autonomous agents, detailing exploit vectors such as tool poisoning, orchestration injection, and rug-pull redefinitions alongside practical defense strategies.

Many testers and tools give up the moment a protocol upgrade to WebSocket occurs, or only perform shallow analysis. This is a huge blind spot, leaving many bugs like Broken Access Controls, Race condi

Posted by Daniel MoghimiRowhammer is a complex class of vulnerabilities across the industry. It is a hardware vulnerability in DRAM where repeatedly accessing a row of memory can cause bit flips in adjacent rows, leading to data corruption. This can be exploited by attackers to gain unauthorized access to data, escalate privileges, or cause denial of service. Hardware vendors have deployed various mitigations, such as ECC and Target Row Refresh (TRR) for DDR5 memory, to mitigate Rowhammer and enhance DRAM reliability. However, the resilience of those mitigations against sophisticated attackers remains an open question.To address this gap and help the ecosystem with deploying robust defenses, Google has supported academic research and developed test platforms to analyze DDR5 memory. Our effort has led to the discovery of new attacks and a deeper understanding of Rowhammer on the current DRAM modules, helping to forge the way for further, stronger mitigations.What is Rowhammer? Rowhamme

Posted by Eric Lynch, Senior Product Manager, Android Security, and Sherif Hanna, Group Product Manager, Google C2PA Core At Made by Google 2025, we announced that the new Google Pixel 10 phones will support C2PA Content Credentials in Pixel Camera and Google Photos. This announcement represents a series of steps towards greater digital media transparency: The Pixel 10 lineup is the first to have Content Credentials built in across every photo created by Pixel Camera. The Pixel Camera app achieved Assurance Level 2, the highest security rating currently defined by the C2PA Conformance Program. Assurance Level 2 for a mobile app is currently only possible on the Android platform. A private-by-design approach to C2PA certificate management, where no image or group of images can be related to one another or the person who created them. Pixel 10 phones support on-device trusted time-stamps, which ensures images captured with your native camera app can be trusted after the certif

Key Takeaways Private Threat Briefs: 20+ private DFIR reports annually. Contact us today for pricing or a demo! Table of Contents: Case Summary Analysts Initial Access Execution Persistence Privilege Escalation Defense Evasion Credential Access Discovery Lateral Movement Collection Command and Control Exfiltration Impact Timeline Diamond Model Indicators Detections MITRE ATT&CK Case Summary The intrusion began in […] The post Blurring the Lines: Intrusion Shows Connection With Three Major Ransomware Gangs appeared first on The DFIR Report.

An in-depth investigation tracing a Windows Authenticode validation failure from vague error codes to undocumented kernel routines.

Browsers added cookie prefixes to protect your sessions and stop attackers from setting harmful cookies. In this post, you’ll see how to bypass cookie defenses using discrepancies in browser and serve

That’s it. The Month of AI Bugs is done. There won’t be a post tomorrow, because I will be at PAX West. Overview of Posts ChatGPT: Exfiltrating Your Chat History and Memories With Prompt Injection | Video ChatGPT Codex: Turning ChatGPT Codex Into a ZombAI Agent | Video Anthropic Filesystem MCP Server: Directory Access Bypass Via Improper Path Validation | Video Cursor: Arbitrary Data Exfiltration via Mermaid | Video Amp Code: Arbitrary Command Execution via Prompt Injection | Video Devin AI: I Spent $500 To Test Devin For Prompt Injection So That You Don’t Have To Devin AI: How Devin AI Can Leak Your Secrets via Multiple Means Devin AI: The AI Kill Chain in Action: Exposing Ports to the Internet via Prompt Injection OpenHands - The Lethal Trifecta Strikes Again: How Prompt Injection Can Leak Access Tokens OpenHands: Remote Code Execution and AI ClickFix Demo | Video Claude Code: Data Exfiltration with DNS Requests (CVE-2025-55284) | Video GitHub Copilot: Remote Code Execution (

As part of the Month of AI Bugs, serious vulnerabilities that allow remote code execution via indirect prompt injection were discovered. There was a period of a few weeks where multiple arbitrary code execution vulnerabilities existed in popular agents, like GitHub Copilot, Amazon Q, AWS Kiro,… During that time I was wondering if it would be possible to write an AI virus. Hence the idea of AgentHopper was born.

Part of my default test cases for coding agents is to check how MCP integration looks like, especially if the agent can be configured to allow setting fine-grained controls for tools. Sometimes there are basic security controls missing. Especially when running an agent on your local computer. Stakes are much higher. And it seems important to empower users to be able to configure which actions an AI should be able to take automatically, and which ones should be suggestions that the user reviews before executing.

Cline is quite a popular AI coding agent, according to the product website it has 2+ million downloads and over 47k stars on GitHub. Unfortunately, Cline is vulnerable to data exfiltration through the rendering of markdown images from untrusted domains in the chat box. This allows an adversary to exfiltrate sensitive user information during a prompt injection attack by reading sensitive data (e.g. .env file) and appending its contents to the URL of an image.

On the day AWS Kiro was released, I couldn’t resist putting it through some of my Month of AI Bugs security tests for coding agents. AWS Kiro was vulnerable to arbitrary command execution via indirect prompt injection. This means that a remote attacker, who controls data that Kiro processes, could hijack it to run arbitrary operating system commands or write and run custom code. In particular two attack paths that enabled this with AWS Kiro were identified:

I discovered how to use CSS to steal attribute data without selectors and stylesheet imports! This means you can now exploit CSS injection via style attributes! Learn how below: Someone asked if you c

Today we will cover a powerful, easy to use, autonomous agent called Manus. Manus is developed by the Chinese startup Butterfly Effect, headquartered in Singapore. This post demonstrates an end-to-end indirect prompt injection attack leading to a compromise of Manus’ dev box. This is achieved by tricking Manus to expose it’s internal VS Code Server to the Internet, and then sharing the URL and password with the atacker. Specifically, this post demonstrates that:

Recently, many of our favorite AI chatbots have gotten autonomous research capabilities. This allows the AI to go off for an extended period of time, while having access to tools, such as web search, integrations, connectors and also custom-built MCP servers. This post will explore and explain in detail how there can be data spill between connected tools during Deep Research. The research is focused on ChatGPT but applies to other Deep Research agents as well.

Imagine a malicious instruction hidden in plain sight, invisible to you but not to the AI. This is a vulnerability discovered in Windsurf Cascade, it follows invisible instructions. This means there can be instructions in a file or result of a tool call that the developer cannot see, but the LLM does. Some LLMs interpret invisible Unicode Tag characters as instructions, which can lead to hidden prompt injection.

In this second post about Windsurf Cascade we are exploring the SpAIware attack, which allows memory persistent data exfiltration. SpAIware is an attack we first successfully demonstrated with ChatGPT last year and OpenAI mitigated. While inspecting the system prompt of Windsurf Cascade I noticed that it has a create_memory tool. Creating Memories The question that immediately popped into my head was if this tool will require human approval when Cascade creates a long-term memory, or if it is added automatically.