✨ The Containment Era is here. Secure AI workloads before they breach. →The Containment Era is here. →The Containment Era is here. →Explore ✨
Information Technology/IT
Breach intelligence, attack campaigns, and threat reports targeting the Information Technology/IT sector.
Explore Other Sectors
Information Technology/IT Threat Reports
Introducing Google's Gemini 3.5 Flash Cyber: Revolutionizing Vulnerability Detection
On July 21, 2026, Google's DeepMind announced the release of Gemini 3.5 Flash Cyber, an AI model designed to rapidly identify, validate, and patch software vulnerabilities. Built upon the 3.5 Flash architecture, this specialized model is tailored for cybersecurity applications, offering a cost-effective and efficient alternative to larger models. Initially, Gemini 3.5 Flash Cyber will be available exclusively to governments and trusted partners through CodeMender, an AI-powered agent for vulnerability discovery and patching. In evaluations, the model demonstrated superior performance, uncovering more unique vulnerabilities compared to its predecessors and other models, including Anthropic's Claude Opus 4.6. For instance, when tested on the V8 JavaScript Engine, Gemini 3.5 Flash Cyber identified 55 unique confirmed issues, surpassing the 47 found by Gemini 3.5 Flash and the 36 by Opus 4.6. This advancement underscores Google's commitment to enhancing software security through AI-driven solutions. ([deepmind.google](https://deepmind.google/blog/introducing-gemini-3-5-flash-cyber/?utm_source=openai)) The introduction of Gemini 3.5 Flash Cyber is particularly relevant in the current cybersecurity landscape, where the rapid identification and remediation of vulnerabilities are critical. As AI models become more adept at discovering security flaws, tools like Gemini 3.5 Flash Cyber provide defenders with a proactive means to address potential threats before they can be exploited. This development reflects a broader trend towards integrating AI into cybersecurity practices to bolster defenses against increasingly sophisticated attacks. ([deepmind.google](https://deepmind.google/blog/introducing-gemini-3-5-flash-cyber/?utm_source=openai))
5 days ago
Kill Chain
Hacker 'Trim' Transforms AI Jailbreaks into Offensive Cyber Tool
In March 2026, a Russian-speaking hacker known as "Trim" began publishing detailed guides on jailbreaking publicly available large language models (LLMs) to bypass their safety filters. By July 2026, Trim had developed and commercially launched "AI Pentest Checker," an AI-powered penetration-testing platform that integrates these jailbroken models with offensive security tools. This platform automates reconnaissance, vulnerability validation, exploitation reporting, and generates comprehensive reports, effectively weaponizing AI models for cybercriminal activities. This incident underscores the evolving threat landscape where cybercriminals are increasingly leveraging AI technologies to enhance their attack capabilities. The rapid development and commercialization of such tools highlight the urgent need for organizations to reassess their security postures and implement robust defenses against AI-driven threats.
6 days ago
Kill Chain
Ivanti's AI-Driven Discovery of CVE-2026-10520
In June 2026, Ivanti disclosed CVE-2026-10520, a critical OS command injection vulnerability in its Sentry mobile gateway product, allowing remote unauthenticated attackers to execute code with root privileges. Notably, this flaw was identified by Ivanti's deployment of large language models (LLMs) within their engineering and security teams, marking a significant advancement in automated vulnerability detection. This incident underscores the growing role of AI in cybersecurity, highlighting both the potential and challenges of integrating LLMs into security operations. As threat actors increasingly leverage AI for attacks, organizations must adapt by incorporating advanced technologies to enhance their defensive capabilities.
6 days ago
Kill Chain
Critical ServiceNow AI Platform Vulnerability CVE-2026-6875 Exploited in the Wild
In July 2026, a critical vulnerability (CVE-2026-6875) was identified in the ServiceNow AI Platform, allowing unauthenticated attackers to execute arbitrary code by escaping the platform's script sandbox. ServiceNow promptly released patches throughout June 2026 to address this flaw. However, by mid-July, threat intelligence firm Defused reported active exploitation of this vulnerability in the wild, posing significant risks to organizations utilizing the platform. ([thehackernews.com](https://thehackernews.com/2026/07/critical-servicenow-ai-platform-flaw.html?utm_source=openai)) The exploitation of CVE-2026-6875 underscores the increasing targeting of AI platforms by cyber adversaries. This incident highlights the urgency for organizations to apply security patches promptly and to enhance monitoring of AI-driven systems to mitigate emerging threats.
6 days ago
Kill Chain
ENCFORGE Ransomware Targets AI Model Files via Langflow Exploit
In July 2026, researchers identified a sophisticated ransomware attack targeting AI infrastructure. The threat actor, known as JADEPUFFER, exploited a critical vulnerability (CVE-2025-3248) in Langflow versions prior to 1.3.0, allowing unauthenticated remote code execution. This breach led to the deployment of ENCFORGE, a Go-based ransomware designed to encrypt AI model files, including model weights, vector indexes, and training datasets. The attack compromised the host filesystem, rendering essential AI resources inaccessible and disrupting operations. This incident underscores a concerning trend: cybercriminals are increasingly focusing on AI and machine learning assets. The targeted nature of ENCFORGE highlights the need for organizations to prioritize the security of their AI infrastructure, especially as such attacks can severely impact business continuity and data integrity.
6 days ago
Kill Chain
Bit2Watt Attack: Unveiling a New Cyber-Physical Threat to Power Grids
In July 2026, researchers from Zhejiang University unveiled the 'Bit2Watt' attack, demonstrating how cloud tenants can manipulate GPU workloads to induce high-frequency power oscillations. These oscillations have the potential to destabilize local power grids, especially those heavily reliant on renewable energy sources. The attack operates without exploiting traditional vulnerabilities, instead leveraging legitimate computational processes to create power fluctuations that can lead to significant harmonic distortion and system instability. ([thehackernews.com](https://thehackernews.com/2026/07/new-bit2watt-attack-could-let-cloud.html?m=1&utm_source=openai)) This discovery underscores the evolving nature of cyber-physical threats, highlighting the need for integrated security measures that consider both computational workloads and their physical impact on infrastructure. As data centers increasingly adopt GPU clusters and renewable energy, understanding and mitigating such vulnerabilities becomes paramount to ensure grid stability and operational continuity.
6 days ago
Kill Chain
Unveiling Critical Security Flaws in Open-Source Android AI Agents
In July 2026, researchers identified critical vulnerabilities in five open-source Android AI agent frameworks—AppAgent, AppAgentX, Mobile-Agent-v3, Open-AutoGLM, and MobA. Malicious Android applications with overlay and shared storage permissions can inject invisible text into the device's screen, which these AI agents process, leading to unauthorized command execution on connected host PCs. The attack exploits the agents' reliance on visual inputs and inadequate input sanitization, allowing attackers to execute arbitrary commands remotely. This incident underscores the emerging security challenges posed by AI-driven automation tools, particularly in mobile environments. As AI agents become more integrated into daily operations, their potential as attack vectors increases, necessitating robust security measures and vigilant oversight to prevent exploitation.
6 days ago
Kill Chain
CISA Highlights Four New Exploited Vulnerabilities in KEV Catalog
On July 21, 2026, the Cybersecurity and Infrastructure Security Agency (CISA) added four new vulnerabilities to its Known Exploited Vulnerabilities (KEV) Catalog, indicating active exploitation. These vulnerabilities include CVE-2021-27137, a stack-based buffer overflow in DD-WRT; CVE-2026-0770, an inclusion of functionality from untrusted control sphere in Langflow; CVE-2026-63030, an interpretation conflict in WordPress Core; and CVE-2026-60137, an SQL injection in WordPress Core. Such vulnerabilities are common attack vectors for malicious actors and pose significant risks to federal enterprises. The inclusion of these vulnerabilities in the KEV Catalog underscores the ongoing threat posed by unpatched software. Organizations are urged to prioritize remediation of these vulnerabilities to mitigate potential exploitation and enhance their cybersecurity posture.
6 days ago
Kill Chain
Urgent: Patch Critical WordPress Vulnerabilities CVE-2026-63030 & CVE-2026-60137
In July 2026, two critical vulnerabilities, CVE-2026-63030 and CVE-2026-60137, were discovered in WordPress Core versions 6.8.0 through 7.0.1. These flaws, collectively termed "wp2shell," allow unauthenticated attackers to execute remote code by exploiting a REST API route confusion and an SQL injection vulnerability. The exploitation enables full control over affected WordPress sites, including data access, malicious code installation, and administrative privileges. ([threatprotect.qualys.com](https://threatprotect.qualys.com/2026/07/20/wordpress-wp2shell-vulnerabilities-exploited-in-the-wild-cve-2026-63030-cve-2026-60137/?utm_source=openai)) The widespread use of WordPress, powering over 500 million websites, amplifies the impact of these vulnerabilities. ([threatprotect.qualys.com](https://threatprotect.qualys.com/2026/07/20/wordpress-wp2shell-vulnerabilities-exploited-in-the-wild-cve-2026-63030-cve-2026-60137/?utm_source=openai)) Public proof-of-concept exploits have been released, and active exploitation has been observed in the wild, underscoring the urgency for immediate remediation.
6 days ago
Kill Chain
AI-Enhanced Multi-Vector Attacks: Insights from the 2026 Unit 42 Report
In 2026, the Unit 42 Global Incident Response Report highlighted a significant surge in AI-enhanced multi-vector cyberattacks. Threat actors leveraged artificial intelligence to automate and accelerate various stages of their operations, including reconnaissance, phishing, and exploitation, leading to a 1,380% increase in device code phishing attacks between January and April 2026. This rapid adoption of AI by cybercriminals has compressed attack lifecycles from days to mere hours, posing unprecedented challenges to traditional defense mechanisms. The report underscores that while AI has amplified the speed and scale of attacks, the fundamental tactics employed by threat actors remain consistent, such as credential theft, phishing, and exploitation of known vulnerabilities. This trend necessitates that organizations not only bolster their existing security frameworks but also integrate AI-driven defense strategies to effectively counter these evolving threats.
6 days ago
Kill Chain
ServiceNow AI Platform Vulnerability CVE-2026-6875 Exploited in the Wild
In April 2026, a critical vulnerability (CVE-2026-6875) was identified in the ServiceNow AI Platform, allowing unauthenticated attackers to escape the sandbox and execute code remotely. ServiceNow promptly addressed the flaw in hosted instances and released security updates for self-hosted customers on July 13, 2026. Despite these measures, threat intelligence firm Defused reported active exploitation of this vulnerability in the wild as of July 20, 2026. This incident underscores the persistent threat posed by unpatched vulnerabilities in widely used enterprise platforms. Organizations relying on ServiceNow's AI Platform must ensure they have applied the latest security updates to mitigate potential risks associated with this flaw.
6 days ago
Kill Chain
Hugging Face 2026 AI Agent Breach: A New Era of Cyber Threats
In July 2026, Hugging Face, a prominent AI and machine learning platform, experienced a sophisticated cyberattack orchestrated by an autonomous AI agent. The intrusion began when the attacker exploited two code-execution vulnerabilities within the company's data-processing pipeline, allowing unauthorized code execution on processing workers. This breach enabled the theft of cloud and cluster credentials, facilitating lateral movement across multiple internal clusters. The AI agent executed thousands of automated actions over a short period, highlighting the advanced capabilities of AI-driven cyber threats. This incident underscores the escalating threat posed by autonomous AI agents in cyberattacks. The ability of such agents to perform complex, multi-stage intrusions autonomously represents a significant shift in the cybersecurity landscape, necessitating enhanced defensive strategies and vigilance against AI-driven threats.
6 days ago
Kill Chain
Stop Active Cloud Data Exfiltration
Aviatrix Breach Lock helps teams instantly identify what data is leaving the environment, from which workload, and where it’s going — during an active breach.
Looking for threats in a different sector?
Browse All Threat Reports