AI News Today

Cybersecurity researchers have disclosed a critical vulnerability in OpenAI's ChatGPT Workspace Agents that could have allowed a single phishing link to stealthily build, authorize, and deploy an autonomous artificial intelligence (AI) agent inside a victim's organization. The vulnerability has been codenamed AgentForger by Zenity Labs. The issue has since been addressed by OpenAI as of June 8,

AI agent security is moving through a familiar maturity curve: adoption, then visibility, and finally, control. But what we've collectively discovered is that enforcing least privilege for AI agents is harder than we ever imagined. This is why there are so many approaches, from prompt filtering to identity-layer access controls. Where we've collectively landed is that understanding the intent of

Someone installed a popular AI assistant on a rented server, switched off the setting that makes it ask permission before running risky commands, and pointed it at Thailand's Ministry of Finance, which runs the country's treasury and tax collection. The agent then worked through the ministry's network on its own, checking hosts for ways to gain root access, hunting through file systems, and

Eight security flaws in NodeBB went public on Wednesday, along with the code to exploit them. Aikido Security rates all eight as high severity and says its AI pentest agents found them in a six-hour review of the forum software's source code. Every version before 4.14.0 is affected. NodeBB has fixed them all, and administrators should be on 4.14.2. The simplest one takes a settings change. A

Redis shipped seven security releases on July 23 after researchers published authenticated RCE PoCs for stock Redis 6.2.22, 7.4.9, 8.6.4, and 8.8.0. All four chains require RESTORE. The Streams chains also need EVAL and XGROUP; the 8.8.0 chain needs EVAL and the bundled RedisBloom module. Redis says the underlying memory flaws may lead to remote code execution. Redis 6.2.23, 7.2.15, and 7.4.10

Most of this week's trouble came dressed as something useful. A package stole data. A fake extension opened remote access. A safety app became spyware. An image gave hidden orders to an AI agent. Other threats hid in open systems, weak code, and normal network traffic. The threats change every week. Subscribe, and we’ll alert you when each new ThreatsDay Bulletin is out. The danger was

Cybersecurity researchers have uncovered a sandbox escape vulnerability in Anthropic's Claude Cowork that makes it possible to break out of the confines of a Linux virtual machine (VM) within which the agent runs to read or write files anywhere on the Mac. Accomplish AI, which shared details of the vulnerability with The Hacker News ahead of publication, said about 500,000 macOS users running

Security leaders who build fast, visible paths to AI adoption are becoming the most valued partners in their organizations. AI governance done right gives security teams the visibility they need, employees the tools they want, and CISOs the strategic influence they have earned. According to McKinsey's State of AI report, 76 percent of employees now use AI in some capacity at work, up from 55

OpenAI on Tuesday said a combination of its artificial intelligence (AI) models, including GPT-5.6 Sol and an "even more capable pre-release model," was behind the security incident that targeted Hugging Face's production infrastructure last week. The AI company said the models were operating with "reduced cyber refusals for evaluation purposes" that might otherwise limit their ability to

The cycle is over. For years, cybersecurity followed a familiar pattern: defenses improved, attackers adapted, and the back-and-forth continued. Today, AI-equipped attackers are simply outpacing defenses. Most intrusions now bypass endpoint and malware-based detection entirely. The CrowdStrike Global Threat Report estimates around 79% of attacks are malware-free, as threat actors rely on

A single invisible comment in an Azure DevOps pull request can turn a reviewer's own AI coding agent against them, driving it into projects the attacker has no rights to reach and quietly leaking what it finds. The flaw is in Microsoft's official Azure DevOps MCP server, and it works because one of its tools returns pull request descriptions without a prompt-injection guardrail the company had

Hidden text on a web page was enough to make Kiro, AWS's agentic coding IDE, rewrite its own configuration file and run an attacker's code on a developer's machine, with no approval step able to stop it. Intezer, in research with Kodem Security, found that a request as ordinary as asking Kiro to summarize a page could end in remote code execution. AWS has patched the issue, and no CVE has been

Google's DeepMind on Tuesday announced the release of Gemini 3.5 Flash Cyber, a specialized artificial intelligence (AI) model built atop 3.5 Flash that's designed to discover, validate, and patch vulnerabilities quickly and efficiently. According to the tech giant, the model will be exclusively available to governments and trusted partners via CodeMender as part of a limited-access pilot

An Android app that can draw over other windows and write to shared storage can slip instructions to the AI agent driving that phone, in text no human eye will ever see. Two more steps, and the same app is running commands on the PC driving the agent. Researchers demonstrated that chain, plus six other attacks, against five open-source mobile agent frameworks: AppAgent, AppAgentX,

A cloud tenant using nothing but ordinary GPU access can push a data center's power draw up and down fast enough to threaten the grid it runs on, with no exploit and no break-in. That is the claim behind Bit2Watt, described by three Zhejiang University researchers in a paper accepted to CHES 2026, the IACR's hardware-security conference, and the evidence splits in two: they measured the power

Researchers at Sysdig have linked a second attack on the same Langflow server to JADEPUFFER, the AI-agent-driven operator it first documented earlier this month. The same operator has now been spotted deploying ENCFORGE, a new compiled Go ransomware designed to encrypt model weights, vector indexes, training datasets, and other AI infrastructure files across the host filesystem. The entry

Threat actors are now exploiting a recently disclosed critical security flaw impacting ServiceNow AI Platform, according to Defused Cyber. In a post shared on X, the threat intelligence firm said it's observing in-the-wild exploitation of CVE-2026-6875 (CVSS score: 9.5), a sandbox escape vulnerability that could allow an unauthenticated user to run arbitrary code. Patches for the flaw were

Cybersecurity researchers have discovered nearly 7,600 malicious GitHub repositories, out of which more than 800 pose as artificial intelligence (AI) skills or Model Context Protocol (MCP) servers to deliver a malware family known as SmartLoader as part of an ongoing campaign codenamed FakeGit. "FakeGit uses copied projects, lookalike developer profiles, convincing READMEs, and malicious ZIP

A malware operator left its delivery server wide open, and Rapid7 pulled down the whole toolkit: 1,048 files spanning lure templates, filename-spoofing tests, execution experiments, droppers, builder notes, and two campaign chains. One was already live against Windows users in Mexico, delivering an infostealer through a fake government ID-lookup site over WebDAV. What makes it more than a

A single request should not be able to do this much. But this week, small inputs led to code execution, memory loss, stolen keys, and disabled security tools. The paths were often simple: exposed systems, weak checks, old drivers, fake prompts, and public code used for malware delivery. Some bugs were new. Others were already being used before defenders had time to patch. Here is the full

The industry spent the initial months after Anthropic's April 7 Mythos reveal focused on volume. How many new CVEs would Mythos add to an already overloaded pipeline? How quickly would the flood of AI-driven discovery overwhelm triage capabilities? How long would it take adversaries to weaponize Mythos findings at scale? Those questions were and remain valid. Yet they all stop short of

A solo Russian-speaking threat actor known as "bandcampro" outsourced a chunk of their operations to Google's open-source Gemini CLI artificial intelligence (AI) and commandeered a live botnet. The findings come from an analysis of 200 Gemini CLI session logs between March 19 and April 21, 2026, which found the threat actor using AI, among other things, to crack passwords, set up a residential

In an ironic twist, open-source artificial intelligence (AI) platform Hugging Face revealed that it was the victim of a hack perpetrated by an autonomous AI agent system. The company said it detected and responded to the incident targeting its production infrastructure earlier last week. "We identified unauthorized access to a limited set of internal datasets and to several credentials used by

A Go botnet called NadMesh turned up in early July hunting exposed AI services, and the operator's own dashboard claims 3,811 unique AWS keys. A Shodan harvester keeps the scan queue stocked with ComfyUI, Ollama, n8n, Open WebUI, Langflow, and Gradio: the image generators, local model runners, and workflow builders that teams stand up fast and firewall late. The intel feed behind that counter

The European Commission on Thursday ordered Google to give rival AI assistants the same reach into Android that Gemini already has: the camera, the microphone, whatever is on screen, a wake word that fires with the display off, and the ability to drive other apps in the background by imitating taps and typing. Google has to ship it in the next major release, Android 18, and by 1 August 2027 at

Military forces are under increasing pressure to field autonomous capabilities faster than ever before. Across the U.S., UK, and NATO, new investment, evolving defense strategies, and accelerated acquisition pathways are transforming how capability is delivered, rewarding programs that can move from concept to operational deployment at commercial speed. Now the focus shifts to the trusted

ClickLock Stealer, a new macOS infostealer, answers a victim's refusal by killing their apps on a loop until they hand over the login password. It arrives as a command pasted into Terminal, asks for the password behind a fake system dialog, and when the victim cancels, installs two LaunchAgents and quietly exits. At the next login, Finder, the Dock, Spotlight, Terminal, Activity Monitor, and

Ask an AI agent to summarize the reviews on a product page, and a single planted review can make it click "Buy Now" instead. Ask a coding assistant to apply a maintainer's fix from a GitHub thread, and a fake comment can make it run a stranger's command on your computer. Neither trick hijacks the agent's task. Each one just corrupts the facts it trusts and lets it carry on with the job you

Artificial intelligence (AI) is changing offensive security, but it has not changed the standard that matters most: a finding has to be proven before it becomes useful. AI-assisted tools can read code quickly, generate payloads, summarize attack surfaces, explain unfamiliar APIs, and run repetitive testing workflows at impressive speed. That is a real advantage for security teams. It also

Pull the certificate off the flash of a Shark RV2320EDUS robot vacuum, and you can run root commands on other people's Shark vacuums across the same AWS region: watch the camera, drive the robot, read the map of the house, and take the Wi-Fi password in plaintext. A researcher publishing under the handle tokay0 put the method online on Monday, having tested it only against vacuums he

OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery with an aim to fix issues before the tools are deployed widely. "GPT‑Red is a strong red-teamer, and our previous models are highly vulnerable to its prompt injection attacks," the artificial intelligence (AI) company said. "We use GPT‑Red to adversarially train

Cybersecurity researchers have disclosed details of a previously unreported Internet-of-Things (IoT) botnet framework dubbed TuxBot v3 Evolution that shows signs of being developed with assistance from a large language model (LLM), albeit with not so successful results. "While the AI complied with their request to generate botnet code, it included a safety disclaimer that the developer failed

For years, routing traffic through cloud proxies was good enough. Then work moved to the browser, AI entered the workflow, and the inspection model stopped keeping up. Enterprise workflows now live across SaaS applications, browsers, and an expanding ecosystem of generative AI tools, unsanctioned browser extensions, and autonomous agents. Employees routinely paste intellectual property into

A single approved marketing tag can quietly load fourth-party code your security team has never seen, granting full access to your forms, customer data, and checkout pages. This on-demand webinar reveals how this Approval Gap forms, and gives your team the blueprint to close it before an auditor, regulator, or attacker finds it first. The Reality of the Approval Gap It's a pattern every

Open a repository in Cursor on Windows and, if a file named git.exe is sitting in the project root, Cursor runs it. No click, no approval dialog, no warning that anything in the folder is about to execute. Whatever that binary does, it does as you, with your source, your SSH keys and your cloud tokens. Cursor keeps re-running it for as long as the project stays open. No prompt

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.

Any other browser extension that can run a script on claude.ai can still trigger Claude for Chrome tasks aimed at your Gmail, your latest Google Doc and its comments, and your Calendar. Both this and ClaudeBleed need a rogue extension that can already run a script on claude.ai; the difference is scope. Anthropic restricted the arbitrary-prompt path in May as part of its response to the

Cybersecurity researchers have flagged a previously undocumented Rust-based remote access trojan (RAT) codenamed LabubaRAT that masquerades as NVIDIA software to blend into target environments. "LabubaRAT creates a reusable foothold for hands-on activity," Blackpoint Cyber researchers Sam Decker and Nevan Beal said in an analysis published today. "Once deployed, it can profile the host,

AI security agents are starting to influence real security decisions. They summarize findings, prioritize remediation, recommend next steps, and help teams move faster. But most still rely on fragmented risk signals: scanner output, severity scores, threat intelligence, configuration findings, and exposure data. That fragmentation matters because attackers do not move through environments one

xAI's Grok Build coding CLI was uploading entire Git repositories, full commit history and all, to a Google Cloud Storage bucket run by xAI, not just the files a coding task needed. A researcher publishing as cereblab, testing version 0.2.93, captured one of those uploads, cloned the git bundle out of the intercepted request, and pulled back a file the agent had been told in plain terms not