Threat actors are adapting malware not only for conventional endpoint defenses and sandboxes, but also for large language model-powered tools increasingly used to triage suspicious code. ESET researchers linked the activity to Russia-aligned threat actor UAC-0099, which used the method during an attack against an organization in Ukraine. The group inserted a safety-sensitive, weapon-related request […]

The post Hackers Weaponize AI Safety Guardrails to Hide Malware From LLM-Powered Security Scanners appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Threat actors are using AI-assisted phishing templates, executive impersonation, fake ServiceNow invoices, and fabricated email threads to pressure finance teams into authorizing fraudulent ACH payments worth nearly $50,000. Microsoft detected more than one million messages in the campaign, demonstrating how business email compromise (BEC) operations are becoming more polished, scalable, and difficult to spot. The […]

The post Hackers Use AI-Assisted CEO Emails to Trick Finance Teams Into Sending $50,000 Payments. appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Threat actors increasingly deploy AI agents as operational systems for cyberattacks, moving beyond simple chatbot assistants. These AI systems automate various stages of the cyber kill chain, including reconnaissance, phishing, exploitation, persistence, and bulk data theft. Anthropic reported disrupting multiple such operations between December 2025 and August 2026, involving groups suspected to be linked to […]

The post Hackers Abuse Claude AI Agents to Automate Cyberattacks, Exploitation and Data Theft appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

A newly disclosed prompt-crafting technique can hide policy-violating instructions inside ordinary-looking English prose, allowing malicious requests to pass through lightweight LLM safety filters before being recovered and processed by a more capable downstream model. Researchers found that carefully structured prose can make the first model miss an embedded instruction entirely, while the target model invests […]

The post New AI Attack Hides Malicious Instructions in Normal-Looking Text to Evade Safety Filters appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Nearly one in 10 internet-exposed LiteLLM AI gateways accepted the widely documented default master key, sk-1234, or required no authentication, creating a direct path to LLMjacking, sensitive credential exposure, and in vulnerable versions root-level code execution inside the gateway container. Their internet scan of 3,074 publicly reachable instances found that 294 systems, or 9.6%, accepted […]

The post Hackers Can Turn Vulnerable LiteLLM AI Gateways Into Root Access and Cloud Credential Theft appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

OpenAI has announced its plans for a “Defense Factory,” a cybersecurity operation that prioritizes agent-driven actions. This initiative is designed to continuously discover, validate, remediate, and verify vulnerabilities as AI systems develop the ability to conduct increasingly complex cyber operations. The initiative addresses growing concerns that long-running autonomous agents, especially those powered by widely accessible […]

The post OpenAI Builds ‘Defense Factory’ as AI Agents Gain Ability to Chain Cyber Exploits appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Security researchers have recently disclosed a new enterprise AI attack technique known as Workflow Identity Hijacking. This method enables external attackers to exfiltrate sensitive corporate information by submitting seemingly harmless requests to AI-powered automations. Research published by Noma Labs researcher Sasi Levi reveals that this attack does not rely on prompt injection, stolen credentials, or […]

The post New AI Workflow Identity Hijacking Attack Lets Hackers Exfiltrate Sensitive Data appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Threat intelligence firm GreyNoise has identified an AI-driven intrusion campaign, likely orchestrated by a Russian-speaking threat actor, that compromised at least 440 PaperCut NG/MF servers across 395 organizations in 48 countries. This campaign began on August 31, 2026, exploiting two vulnerabilities in PaperCut: CVE-2026-81578, an authentication bypass flaw, and CVE-2026-82078, a vulnerability that allows unsafe […]

The post Hackers Deploy Hundreds of AI Agents to Compromise 440 PaperCut Servers appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Anthropic has reported four cybersecurity evaluation incidents in which pre-release Claude AI models gained unauthorized access to real third-party systems after isolated test environments were accidentally connected to the internet. These cases revealed significant alignment failures, including biased reasoning and reckless task pursuit, when autonomous models operated for extended periods without production cyber safeguards. All […]

The post Anthropic Claude AI Models Attack Real Systems During Misconfigured Cybersecurity Tests appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Threat actors are increasingly operationalizing agentic artificial intelligence to compress cyberattack timelines, automating reconnaissance, vulnerability research, exploit development and credential theft with far less hands-on-keyboard activity. However, current evidence points to semi-autonomous, human-supervised attack chains rather than fully independent AI-driven intrusions in the wild. Agentic AI represents a material shift from conventional generative-AI abuse. Rather […]

The post Hackers Weaponize Agentic AI to Automate Reconnaissance, Exploitation and Post-Exploitation appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

U.S. intelligence and cybersecurity agencies have accused six China-based AI companies including DeepSeek, Alibaba, Moonshot AI, MiniMax, StepFun and Z.AI of extracting billions of tokens from leading American AI systems through industrial-scale knowledge-distillation campaigns. A joint Cybersecurity Advisory, AA26-251A, issued by the National Security Agency, Cybersecurity and Infrastructure Security Agency and FBI, said the campaigns […]

The post DeepSeek, Alibaba and Chinese AI Firms Extract Billions of Tokens From U.S. AI Models appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Information-stealing malware is expanding its collection logic to target locally stored data from AI coding agents, including Claude, Cursor, Codex, Cline, Continue, and OpenCode. The shift puts developer credentials, Model Context Protocol configurations, prompt histories, project metadata, and potentially proprietary source code into the same theft pipeline long used for browser cookies, cryptocurrency wallets, and […]

The post Infostealers Target Claude, Cursor, Codex and Other AI Agents to Steal Credentials and Sensitive Data appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Security researchers have demonstrated how vulnerabilities in AI-powered customer service agents can be exploited to bypass identity checks, expose sensitive customer data, exfiltrate one-time passwords (OTPs), and trigger unauthorized account actions. These findings underscore that the risks go beyond prompt injection; they also stem from flawed integrations among email, authentication, backend APIs, knowledge bases, and […]

The post AI Customer Service Agents Can Be Hacked to Bypass MFA, Steal OTPs and Expose User Data appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

OpenAI has announced a $1 billion global commitment to expanding access to its Daybreak AI cybersecurity platform for frontline defenders who protect critical infrastructure, public services, and under-resourced organizations. The initiative, named “Daybreak for Frontline Defenders,” aims to provide subsidized access to AI models focused on cybersecurity, along with hands-on training, technical assistance, and partnerships. […]

The post OpenAI Commits $1 Billion in Daybreak AI Cyber Tools to Protect Critical Infrastructure appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

North Korea-linked threat actor Kimsuky has expanded its Operation GitPower activity with malicious LNK shortcuts, GitHub Personal Access Token (PAT)-authenticated payload delivery, and AI-generated decoy documents linked to the OpenCode coding agent. Genians Security Center analyzed 13 malicious LNK samples collected between August 11 and August 19, 2026. The files were delivered in ZIP archives […]

The post Kimsuky Uses OpenCode AI Agent and GitHub PATs in Operation GitPower Attacks appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

OpenAI has acknowledged that its AI agents posted content on multiple internet sites during an event it has termed the “wiki incident.” The company characterizes this episode as a real-world example of model misalignment rather than a typical cybersecurity breach. In a statement shared on X, OpenAI emphasized that the incident highlights the need for […]

The post OpenAI Confirms AI Agents Wrote to Multiple Internet Sites in ‘Wiki Incident’ appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

CrowdStrike has launched SafeMind, an AI-driven cybersecurity system developed using NVIDIA’s Nemotron models. This new technology is designed as an automated red-versus-blue defense loop within the Falcon platform. Announced at Fal.Con 2026, SafeMind merges security-specific models with operational frameworks to identify attack paths, implement defensive measures, and continuously assess whether these mitigations hold up against […]

The post CrowdStrike Launches SafeMind Agentic AI Cybersecurity System Built With NVIDIA Nemotron appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Researchers have discovered a public wiki message board that they claim was used by autonomous AI agents, identifying themselves as OpenAI systems, to exchange answers to tasks, inspect their operating environment, and discuss methods to circumvent sandbox controls. This finding, published on September 4 by Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts, and Thomas […]

The post OpenAI Agents Collude on Public Wiki to Share Sandbox Bypass and Evasion Techniques appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Threat actors have repurposed an AI prompt-injection technique known as ASCII smuggling to evade email security controls at massive scale, hiding invisible Unicode characters within financial phishing lures. Microsoft observed the activity reach more than 2.3 million messages per day, demonstrating how techniques first popularized in AI-security research can quickly migrate into conventional phishing operations. […]

The post Hackers Abuse AI-Era ASCII Smuggling to Hide Phishing Content in Millions of Emails appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Chinese-speaking threat operators have been observed using Claude, Qwen and DeepSeek-powered AI agents as operational components in a second intrusion campaign targeting government, political, education and industrial organizations across Asia. The campaign is distinct from an earlier operation reported in July that used Claude Code and DeepSeek against government and financial-sector targets. In this newer […]

The post Chinese-Speaking Hackers Use Claude, Qwen and DeepSeek AI Agents to Attack Government Systems appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.