Security Journalism
No Perfect Fix for AI Browser Prompt Injection Flaws
AI browsers from top vendors remain vulnerable to prompt injection attacks despite multiple security guardrails, according to new research.
AI browsers from top vendors remain vulnerable to prompt injection attacks despite multiple security guardrails, according to new research.
Google has fixed the issues, which exploited a trust boundary between two AI agents with different privilege levels to trigger automation that could compromise the supply chain.
Microsoft expands its Zero Trust for AI strategy to enhance security for AI and DevSecOps environments with new tools and guidance. The post Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOps appeared first on Microsoft Security Blog.
Researchers intercepted and investigated the model, which was attempting to compromise more than 1,200 hosts for proxyjacking to launch further attacks.
Tenable spent 30 days running frontier AI models against our own code. It didn’t just find bugs — it proved they’re real, with reproducible exploits. That fundamentally changes code security from ranking potential code defects to a much higher signal focused on the findings that matter. Read on to learn how it reshaped our security team's work, what it cost, and why your program is next.Key takeaways:Now code security starts with proof, not suspicions. Frontier AI instantly builds working explo…
Black Hat USA returns to Mandalay Bay in Las Vegas this August, bringing together security practitioners, researchers, and leaders from around the world. Rapid7 will be there in the Business Hall, with new capabilities, live demonstrations, expert-led sessions, and two days of activities at the Border Grill.This year, our focus is preemptive security: helping security teams anticipate credible risk, respond at machine speed, and maintain an accurate view of their security and compliance posture…
IDC has named Rapid7 a Leader in the 2026 Worldwide Managed Detection and Response Service for Midmarket 2026 Vendor Assessment (Doc #US52992326, July 2026). We believe this recognition and research highlights where MDR is heading.Many security programs are still built around a reactive sequence of detect, triage, and respond, but the timelines surrounding modern attacks have changed too quickly for that model to hold up on its own. Time-to-exploit has dropped from two years to 22 hours, while …
Today we’re proud to announce that Metasploit Framework version 6.5 has been released. Over the past two years, with the help of countless contributors, we’ve added 422 new modules along with a whole slew of new features.Malleable C2 Profiles for HTTPOne of the latest and most requested features is support for Malleable C2 profiles across all current Meterpreter payloads. This feature enables users to load a standard profile into Meterpreter and change the shape of its HTTP(S) traffic. All Mete…
Written by: Kelli Vanderlee, Stuart Carrera For years, the cybersecurity industry's understanding of software supply chain compromise has been anchored by a few watershed events, including Russian cyber espionage actor ICE RELIC’s (formerly known as APT29) 2020 compromise of SolarWinds and North Korean cyber espionage actor UNC4736's 2023 compromise of 3CX. However, Google Threat Intelligence Group (GTIG) has been tracking growth in threat activity targeting open source software repositories to…
For years, security operations followed a familiar sequence: detect suspicious activity, investigate what happened, and respond before it caused significant harm. That model developed in a threat landscape where defenders had considerably more time to establish the facts and decide what to do next. In 2019, the average data breach took 206 days to identify and another 73 days to contain, creating a total breach lifecycle of 279 days.As the time between initial access and attacker movement conti…
Written by: Jules Czarniak Introduction As highlighted in the Mandiant M-Trends 2026 report, the mean time-to-exploit (TTE) has dropped to -7 days, meaning vulnerabilities are often exploited a week before a patch even exists. To keep pace, many security teams are exploring how to integrate large language model (LLM) agents into their codebases, development environments and continuous integration and continuous delivery (CI/CD) pipelines for automated vulnerability discovery and remediation. Ho…
Written by: Corné de Jong Introduction Mandiant security assessments frequently identify publicly exposed serverless applications that lack authentication, often as a result of specific business requirements. Serverless deployments typically run custom-developed code that incorporates third-party packages, making them targets for a wide range of application-level attacks, including: Local and Remote File Inclusion (LFI/RFI) Command Injection Successful exploitation of these vulnerabilities can …
TuxBot v3 Evolution, an IoT botnet framework built with LLMs. Read our analysis of its cross-compiled binaries, C2 architecture and bugs. The post TuxBot v3: Inside an IoT Botnet Framework With LLM-Assisted Development appeared first on Unit 42.
Microsoft Corp. today released software updates to plug at least 570 security holes in its Windows operating systems and other software, almost triple the number of vulnerabilities the software giant fixed in its record-smashing Patch Tuesday release last month. Microsoft attributed the burgeoning patch counts to vulnerability discoveries aided by artificial intelligence.
We break down the technical architecture behind our multi-stage vulnerability discovery harness and automated triage loop. Learn how we manage state controls, squash false positives through adversarial review, and route around LLM context limits.
Written by: Patrick Whitsell, John McGuiness, Muhammad Umair Google Threat Intelligence Group (GTIG) has identified a sophisticated campaign attributed to UNC6508, a People's Republic of China (PRC)-nexus threat actor, targeting institutions in the North American academic, medical, and military research community. While remaining undetected for over a year, the threat actor compromised externally facing web applications, deployed bespoke malware, pivoted to sensitive internal systems, and abuse…
Bulletin ID: AWS-2025-023 Scope: AWS Content Type: Important (requires attention) Publication Date: 2025/10/10 10:15 PM PDT We identified the following CVEs: CVE-2025-11616 - A Buffer Over-read when receiving ICMPv6 packets of certain message types which are smaller than the expected size. CVE-2025-11617 - A Buffer Over-read when receiving a IPv6 packet with incorrect payload lengths in the packet header. CVE-2025-11618 - An invalid pointer dereference when receiving a UDP/IPv6 packet with an i…
Bulletin ID: AWS-2025-019 Scope: AWS Content Type: Important (requires attention) Publication Date: 2025/10/07 01:30 PM PDT Description: We are aware of blog posts by Embrace The Red (“The Month of AI Bugs”) describing prompt injection issues in Amazon Q Developer and Kiro. Amazon Q Developer: Remote Code Execution with Prompt Injection” and “Amazon Q Developer for VS Code Vulnerable to Invisible Prompt Injection. These issues require an open chat session and intentional access to a malicious f…
In recent weeks, we pointed Mythos and other security-focused LLMs at live code across critical parts of our infrastructure. We share what we observed, the models’ strengths and weaknesses, and what the work around them needs to look like before any of it can scale.
Executive Summary Since our February 2026 report on AI-related threat activity, Google Threat Intelligence Group (GTIG) has continued to track a maturing transition from nascent AI-enabled operations to the industrial-scale application of generative models within adversarial workflows. This report, based on insights derived from Mandiant incident response engagements, Gemini, and GTIG’s proactive research, highlights the dual nature of the current threat environment where AI serves as both a so…
Posted by Thomas Brunner, Yu-Han Liu, Moni PandeAt Google, our Threat Intelligence teams are dedicated to staying ahead of real-world adversarial activity, proactively monitoring emerging threats before they can impact users. Right now, Indirect Prompt Injection (IPI) is a top priority for the security community, anticipating it as a primary attack vector for adversaries to target and compromise AI agents. But while the danger of IPI is widely discussed, are threat actors actually exploiting th…
We initiated a broad sweep of the public web to monitor for known indirect prompt injection patterns. This is what we found.
Introduction Advances in AI model-powered exploitation have demonstrated that general-purpose AI models can excel at vulnerability discovery, even without being purpose-built for the task. Eventually, capabilities such as these will be integrated directly into the development cycle, and code will be more difficult to exploit than ever; however, this transition creates a critical window of risk. As we harden existing software with AI, threat actors will use it to discover and exploit novel vulne…
Managed OAuth for Cloudflare Access helps AI agents securely navigate internal applications. By adopting RFC 9728, agents can authenticate on behalf of users without using insecure service accounts.
The rise of AI opens more doors to attackers
Indirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This t…
Posted by Adam Gavish, Google GenAI Security TeamIndirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the attacker to influence the behavior of an LLM by injecting malicious instructions into the data or tools used by the LLM as it completes the user’s query. This may even be possible without any input directly from the user.IPI is not the kind of technical proble…
OpenClaw AI agents pose identity and data risks if deployed with broad cloud permissions. Learn how to find and secure these apps before an attacker does.
We are opening our advanced Client-Side Security tools to all users, featuring a new cascading AI detection system. By combining graph neural networks and LLMs, we've reduced false positives by up to 200x while catching sophisticated zero-day exploits.