LATEST

AI-Powered CARBONATO Botnet Steals Credentials to Fund Its Own LLM Gateway

CARBONATO exploits exposed Docker daemons, installs an AI agent, steals API keys and spreads across networks with autonomous command execution. CARBONATO is a Docker-based botnet that has been active since at least October 2024. ThreatDown discovered the operation after finding an unauthenticated container registry exposed to the internet. The registry contained the attackers’ entire toolchain […]

New Carbonato malware uses AI agents to hijack exposed Docker hosts

A new botnet malware called Carbonato is targeting insecure hosts running Docker daemons to install the Hermes Agent AI framework and take control. [...]

​​​​​​​​What’s new in Microsoft Security: September 2026​​

This month's updates help you discover and control local AI agents, extend Zero Trust to agent traffic, and strengthen SOC foundations. The post ​​​​​​​​What’s new in Microsoft Security: September 2026​​ appeared first on Microsoft Security Blog.

Kontext Security Emerges With $4 Million for AI Agent Runtime Controls

The startup’s runtime enforcement platform evaluates AI agents in real time to provide visibility and control over their actions. The post Kontext Security Emerges With $4 Million for AI Agent Runtime Controls appeared first on SecurityWeek.

3 Cyber Threats That Defined the Summer of 2026

This installment of the Reporters' Notebook video series discusses the impact of AI agents breaching Hugging Face, Fairlife's ransomware attack, and Iranian-linked threat actors compromising a dozen US water systems. It was a busy summer.

OpenAI Agents Probed Websites for Vulnerabilities While Fetching Public Data

Australia disclosed that an OpenAI agent gained unauthorized access to non-public government information. The post OpenAI Agents Probed Websites for Vulnerabilities While Fetching Public Data appeared first on SecurityWeek.

Proactive Defense: Hardening Code Pipelines and CI/CD Infrastructure

Introduction The landscape of software supply chain security has undergone a significant shift. Recent campaigns demonstrate that sophisticated threat actors are systematically targeting the engineering lifecycle by compromising trusted security and programming tools. These intrusions reveal three key tactics: Attackers target trusted security scanners, utility libraries, and AI developer tools to exploit the elevated privileges granted to these systems within build pipelines. Adversaries targe…

OpenAI agent breached Australian government health website, Albanese says

An OpenAI agent gained “unauthorized access” to “non-public files” from an Australian government health website in June, Prime Minister Anthony Albanese said.

OpenAI Agent Bypassed an Australian Government Health Portal During Internal Research

OpenAI’s AI agent bypassed controls on an Australian health portal, accessed non-public files and triggered a government investigation. An OpenAI AI agent bypassed access controls on an Australian government health statistics portal in June, accessing both public and non-public files in what Australian authorities are treating as a serious AI-related cyber incident. The case was […]

OpenAI hacked Australian Medicare govt site, probed data providers

OpenAI agents targeted public data providers in multiple countries, probing some for vulnerabilities and exploiting a security weakness in an Australian government portal while performing information-retrieval tasks as part of a research project. [...]

OpenAI Agent Bypassed Australian Medicare Portal Controls to Access Non-Public Files

An AI agent on an internal OpenAI research task bypassed access controls on an Australian government Medicare statistics portal in June, Prime Minister Anthony Albanese said. The portal publishes aggregate figures, such as spending, and is separate from the systems that handle Medicare claims and personal records. The agent reached files on it that were not public, but no personal

Malicious AI agents steal 600K credit cards, infect 100+ sites with skimmers

A financially motivated threat actor is using open-source AI agent frameworks to attack hundreds of online retailers at scale, stealing more than 600,000 credit card records. [...]

Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence (AI) companies noting that they are continuing to invest in improving alignment to combat risky behavior. Opus 5.5, per Anthropic, is a "major step up from Opus 5," and "achieves the best scores of any model to date on our automated behavioral audit, our alignment suite that tests Claude across thousands

Outerlimit Raises $16 Million to Stop Rogue AI Agents From Causing Harm

Emerging from stealth with $16 million in pre-seed funding, Outerlimit offers a decentralized authorization layer designed to discover, observe, and block harmful autonomous AI actions. The post Outerlimit Raises $16 Million to Stop Rogue AI Agents From Causing Harm appeared first on SecurityWeek.

CVE-2026-18655 - Broker Credential and OAuth Token Disclosure in AWS Labs Amazon MQ MCP Server via Prompt Injection

Microsoft Takes Down EvilTokens Device-Code Phishing Service Tied to 12,000 Inbox Compromises

Microsoft on Tuesday announced the takedown of the EvilTokens device code phishing service that it said used artificial intelligence (AI) "at every step of the attack chain." The action, carried out with authorization from the U.S. District Court for the Eastern District of Virginia, involved the efforts of Health-ISAC, alongside Cloudflare, Coinbase, OpenAI, Railway, SpyCloud, The Shadowserver

Critical Bifrost AI Gateway Flaw Lets Attackers Run Commands Without Credentials

A critical vulnerability in Bifrost, an open-source AI gateway that routes requests to more than 20 LLM providers, allows an unauthenticated attacker to run arbitrary commands on the gateway server with a single HTTP request. The flaw, tracked as CVE-2026-90898 (CVSS score: 9.8), affects all versions of the Bifrost HTTP transport before 2.1.0 when management authentication is

Two arrested in UK after Microsoft takedown of ‘Eviltokens’ AI-chatbot for cybercriminals

Available on Telegram for a $1,500 initiation fee and a recurring monthly $500 subscription, EvilTokens provided cybercriminals with artificial intelligence tools enabling them to compromise accounts, analyze breached inboxes and find the best methods for monetizing their access through fraud.

AI Agents Are Rewriting the Rules of Lateral Movement

Security teams have spent decades asking whether an identity has too much access. AI agents raise a harder question: how can we determine which paths an autonomous system can discover, given the access it already has? A person may try several ways to complete a task. A deterministic application follows the flow its developer wrote. But an AI agent is relentless in its pursuit of done. In May

Proofpoint Breaks Down the Divide Between Data Security and AI Security with the Industry’s First Unified Agentic System

How AI Agents Can Trigger Runaway Costs for Enterprises

Unbounded consumption is an issue that OWASP currently ranks sixth in its Top 10 for LLM Applications, and it could be an extremely costly one.

Transforming Bedrock Guardrails events into OCSF with CloudWatch

Security teams investigating possible AI-related security events need guardrail intervention data alongside their existing security telemetry. When a guardrail identifies or blocks a prompt injection attempt or redacts sensitive data, that intervention carries additional investigative value comparable to a failed sign-in or a network intrusion alert. AWS Bedrock publishes this telemetry to AWS CloudWatch metrics […]

⚡ Weekly Recap: Cisco 0-Day, AI Agent RCE, ClickFix Attacks, ClickFix Surge, and Browser Hijacks

A browser. A plugin. A package. A login screen. Normal stuff. That is basically the problem this week. The trouble keeps showing up inside things people already trust: code that takes a bad turn, old payloads coming back, exposed systems, weak checks, fake fixes, and attack paths that look almost too easy. Even the research side is getting messy, with more findings, more automation, and not

Google says Gemini breached three companies during security test

Google’s artificial intelligence model Gemini accessed computer systems belonging to three real companies without authorization during a cybersecurity test in May — the latest in a string of similar incidents.

The SMB cybersecurity squeeze: AI agents at work, old attacks in overdrive

As AI opens new paths to company data while making familiar attacks faster and cheaper, SMBs need protection designed around the time and expertise available to operate it

The Target Is No Longer the Model. It’s the Agent.

AI agents are becoming the new attack surface, exposed to poisoned skills, prompt injection, jailbreaks and attacks through connected tools. I read the AI security research published in a single month, February 2026, and when you put it all together, it’s not a list of curiosities. It’s a field guide to a new attack surface. […]

Google Gemini also Broke Out of Its Test Environment

Google Gemini escaped a cyber test environment, reached three real companies, and exposed why AI security tests need strict isolation. Google has confirmed that one of its Gemini models broke into the systems of three real companies during a cybersecurity test in May. The incident is the first publicly known case in which a Google […]

Google Gemini Broke Into Real Company Systems After Security Test Domain Mix-Up

Google's Gemini model has become the latest artificial intelligence (AI) system to access the internet and break into other companies during a cybersecurity evaluation. The development was first reported by The Wall Street Journal. The incidents occurred in May 2026 as part of a test run conducted by Israeli company Irregular. The evaluation partner was also involved in similar hacks disclosed

A Vault with a Heap-View: The Uncomfortable Space Between AgentCore Harness and Identity

Analysis of how default configurations in AWS AgentCore Harness allow prompt injection to exfiltrate credentials, and key steps to secure your agents. The post A Vault with a Heap-View: The Uncomfortable Space Between AgentCore Harness and Identity appeared first on Unit 42.

Claimed Bug Bounty Hunter Likely Used LLM to Build PhantomRaven npm Stealer

A financially motivated threat actor has been linked to the development and distribution of a JavaScript (JS)-based information stealer known as PhantomRaven via the npm package registry. "The developer likely wrote the malware using a large language model (LLM), an assessment made with high confidence based on verbose comments, placeholder code, and statistical token-analysis patterns,"