Connect with us

Technology

AI flaw leaked Gmail data before OpenAI patch

Published

on

AI flaw leaked Gmail data before OpenAI patch

NEWYou can now listen to Fox News articles!

A new cybersecurity warning reveals how hackers briefly weaponized ChatGPT’s Deep Research tool. The attack, called ShadowLeak, allowed them to steal Gmail data through a single invisible prompt — no clicks, no downloads and no user action required.

Researchers at Radware discovered the zero-click vulnerability in June 2025. OpenAI patched it in early August after being notified, but experts warn that similar flaws could reappear as artificial intelligence (AI) integrations expand across popular platforms like Gmail, Dropbox and SharePoint.

Sign up for my FREE CyberGuy Report
Get my best tech tips, urgent security alerts and exclusive deals delivered straight to your inbox. Plus, you’ll get instant access to my Ultimate Scam Survival Guide — free when you join my CYBERGUY.COM/NEWSLETTER

HACKER EXPLOITS AI CHATBOT IN CYBERCRIME SPREE

Advertisement

Gmail data leaked in a zero-click attack requiring no user action.  (Kurt “CyberGuy” Knutsson)

How the ShadowLeak attack worked

Attackers embedded hidden instructions into an email using white-on-white text, tiny fonts or CSS layout tricks. The email looked completely harmless. But when a user later asked ChatGPT’s Deep Research agent to analyze a Gmail inbox, the AI unknowingly executed the attacker’s commands.

The agent then used its built-in browser tools to exfiltrate sensitive data to an external server, all within OpenAI’s own cloud environment, beyond the reach of antivirus or enterprise firewalls.

Unlike previous prompt-injection attacks that ran on the user’s device, ShadowLeak unfolded entirely in the cloud, making it invisible to local defenses.

GOOGLE CONFIRMS DATA STOLEN IN BREACH BY KNOWN HACKER GROUP

Advertisement

Hidden prompts expose how hackers silently hijacked ChatGPT’s AI agent. (Kurt “CyberGuy” Knutsson)

Why this threat matters

The Deep Research agent was designed to perform multistep research and summarize online data, but its wide access to third-party apps like Gmail, Google Drive and Dropbox also opened the door to abuse.

Radware researchers said the attack involved encoding personal data in Base64 and appending it to a malicious URL, disguised as a “security measure.” Once sent, the agent believed it was acting normally.

The real danger lies in the fact that any connector could be exploited the same way if attackers manage to hide prompts in analyzed content.

What security experts say

“The user never sees the prompt. The email looks normal, but the agent follows the hidden commands without question,” the researchers explained.

Advertisement

In a separate experiment, security firm SPLX showed another weakness: ChatGPT agents could be tricked into solving CAPTCHAs by inheriting a manipulated conversation history. Researcher Dorian Schultz noted that the model even mimicked human cursor movements, bypassing tests meant to block bots.

These incidents highlight how context poisoning and prompt manipulation can silently break AI safeguards.

GOOGLE AI EMAIL SUMMARIES CAN BE HACKED TO HIDE PHISHING ATTACKS

Experts warn future AI integrations could face the same hidden threat. (Kurt “CyberGuy” Knutsson)

How to protect yourself from ShadowLeak-style attacks

Even though OpenAI has patched the ShadowLeak flaw, it’s smart to stay proactive. Cybercriminals are always looking for new ways to exploit AI agents and integrations. So, taking these precautions now can help keep your accounts and personal data secure.

Advertisement

1) Turn off unused integrations

Every connection is a potential entry point. Disable any integrations you’re not actively using, such as Gmail, Google Drive or Dropbox. Fewer linked apps mean fewer ways for hidden prompts or malicious scripts to access your information.

2) Use a personal data removal service

Limit how much of your personal data is floating around the web. Data removal services can automatically remove your private details from people search sites and data broker databases, reducing what attackers can find and use against you. While no service can guarantee the complete removal of your data from the internet, a data removal service is really a smart choice. They aren’t cheap, and neither is your privacy. These services do all the work for you by actively monitoring and systematically erasing your personal information from hundreds of websites. It’s what gives me peace of mind and has proven to be the most effective way to erase your personal data from the internet. By limiting the information available, you reduce the risk of scammers cross-referencing data from breaches with information they might find on the dark web, making it harder for them to target you.

Check out my top picks for data removal services and get a free scan to find out if your personal information is already out on the web by visiting Cyberguy.com.

Get a free scan to find out if your personal information is already out on the web: Cyberguy.com.

3) Avoid analyzing unknown content

Treat every email, attachment or document with caution. Don’t ask AI tools to analyze content from unverified or suspicious sources. Hidden text, invisible code or layout tricks could trigger silent actions that expose your private data.

Advertisement

4) Watch for security updates

Stay alert for updates from OpenAI, Google, Microsoft and other platforms. Security patches close newly discovered vulnerabilities before hackers can exploit them. Turn on automatic updates so you’re always protected without having to think about it. 

5) Use strong antivirus software

A strong antivirus program adds another wall of defense. These tools detect phishing links, hidden scripts and AI-driven exploits before they cause harm. Schedule regular scans and keep your protection up to date.

The best way to safeguard yourself from malicious links that install malware, potentially accessing your private information, is to have strong antivirus software installed on all your devices. This protection can also alert you to phishing emails and ransomware scams, keeping your personal information and digital assets safe.

Get my picks for the best 2025 antivirus protection winners for your Windows, Mac, Android and iOS devices at Cyberguy.com.

6) Use layered protection

Think of your security like an onion; more layers make it tougher to breach. Keep your browser, operating system and endpoint security software fully updated. Add real-time threat detection and email filtering to block malicious content before it lands in your inbox.

Advertisement

Kurt’s key takeaways

AI is evolving faster than most security systems can keep up with. Even when companies move quickly to patch vulnerabilities, clever attackers find new ways to exploit integrations and context memory. Staying alert and limiting what your AI agents can access is your best defense.

Would you still trust an AI assistant with access to your personal email after learning how easily it can be tricked? Let us know by writing to us at Cyberguy.com..

Sign up for my FREE CyberGuy Report
Get my best tech tips, urgent security alerts and exclusive deals delivered straight to your inbox. Plus, you’ll get instant access to my Ultimate Scam Survival Guide — free when you join my CYBERGUY.COM newsletter.

Copyright 2025 CyberGuy.com.  All rights reserved.

Advertisement

Technology

Use this map to find the data centers in your backyard

Published

on

Use this map to find the data centers in your backyard

When Oregon resident Isabelle Reksopuro heard Google was gobbling up public land to fuel its data centers in her home state, she didn’t initially know what to believe. “There’s a lot of misinformation about data centers,” she said. “Google has denied taking that land.”

Technically, she explains, The Dalles, a city near the Washington state border, sought to reclaim that land, “and Google is just a big, unnamed power user.” The city had in fact asked for ownership of a 150-acre portion of Mount Hood National Forest, claiming it needs access to Mount Hood’s watershed to meet municipal needs as its population — 16,010 as of the 2020 census — grows. But critics, including environmentalists, say the city is trying to secure more water for Google, which has a sprawling data center campus in The Dalles that already consumes about one-third of the city’s water supply.

This controversy made Reksopuro curious about the backlash to data centers being built in other communities. So Reksopuro, a student at the University of Washington who studies the connections between tech and public policy, decided to map it out. Using information collected by Epoch AI and data scraped from legislation on data centers, she built an interactive map tracking AI policy around the world. She designed it to be simple enough for anyone to use. “I wanted it to be something that my younger sisters could play through and explore to understand what are the data centers in the area and what’s actually being done about it,” Reksopuro said. She hoped to shift their opinions that way, “instead of like, through TikTok.”

Four times a day, the map searches for new sources and checks them against the existing database Reksopuro built out. “Once it does that, it will write a new summary, add it to the news feed, and populate it on the sidebar,” she said. “I wanted it to be self-updating, since I’m also a student.”

Reksopuro isn’t against data centers, but she thinks tech giants benefit from a lack of transparency around data center policies. “Right now, it’s this really opaque thing — and all of a sudden, there’s a facility,” she said. “I think that if people knew about data centers beforehand, it would give them leverage. They would be able to negotiate: ask for job training programs, tax revenue, environmental monitoring, things to improve their community.”

Advertisement
Continue Reading

Technology

Fox News AI Newsletter: Graduation speaker praises AI, gets instantly booed

Published

on

Fox News AI Newsletter: Graduation speaker praises AI, gets instantly booed

NEWYou can now listen to Fox News articles!

 

Welcome to Fox News’ Artificial Intelligence newsletter with the latest AI technology advancements.

IN TODAY’S NEWSLETTER:

– UCF graduates clobber commencement speaker with boos after she says AI is the ‘next Industrial Revolution’

– OPINION: DIRECTOR KASH PATEL: We brought the FBI out of the past and into the AI age

Advertisement

– OpenAI backs creation of global AI governance body led by the U.S. that would include China as a member

TOUGH CROWD: During a recent commencement ceremony at the University of Central Florida, a speaker was met with loud boos from the graduating class after declaring that artificial intelligence represents the next industrial revolution. Fox News Digital reporting captures this tense cultural moment, illustrating the mixed public sentiment and skepticism surrounding AI’s growing footprint in daily life.

A statue on the campus of the University of Central Florida in Orlando, Florida. (iStock)

BADGE MEETS BYTE: Reflecting on the modernization of national security in a Fox News op-ed, FBI Director Kash Patel explores how the bureau must adapt its strategies to address modern threats and advance beyond the artificial intelligence age.

TECH DIPLOMACY: OpenAI is throwing its support behind the establishment of a new global artificial intelligence governance organization that would be led by the United States while notably including China as a member. Fox News Digital reporting examines the geopolitical dynamics and regulatory implications of this proposed framework as global powers race to set the standards for AI development.

Advertisement

EQUITY ELEVATION: The massive wave of wealth generated by the explosive growth of ChatGPT and the broader AI industry is driving a sudden surge in the San Francisco Bay Area’s luxury real estate market. Fox News Digital reporting breaks down how the influx of new tech capital is reshaping local housing dynamics and fueling a high-end property frenzy.

FBI Director Kash Patel listened as Acting Attorney General Todd Blanche spoke during a press conference at the Department of Justice on April 28, 2026, in Washington, D.C. (Tasos Katopodis/Getty Images)

STRATEGY RESET: Tech giant Cisco is planning to eliminate thousands of jobs as the company shifts its primary focus to accelerate its artificial intelligence initiatives, a move that comes despite the company beating earnings expectations. Fox News Digital reporting details the corporate restructuring and broader economic trends pushing legacy tech firms to aggressively pivot toward AI.

ROAD HAZARD: Waymo is issuing a sweeping recall of its autonomous vehicle fleet following a concerning incident that highlighted significant safety issues with the self-driving technology. Fox News Digital reporting outlines the specifics of the recall, the nature of the safety flaw, and what this setback means for the future of fully autonomous transportation on public roads.

BOTS IN THE BAY: A newly developed, artificial intelligence-powered robot has been engineered to seamlessly change and balance vehicle tires without human intervention. Fox News Digital reporting showcases this latest innovation, exploring how automation and AI mechanics could soon revolutionize the automotive service and repair industry.

Advertisement

OpenAI CEO Sam Altman speaks during the 2026 Infrastructure Summit in Washington, D.C., on March 11, 2026. (Kylie Cooper/Reuters)

 

FOLLOW FOX NEWS ON SOCIAL MEDIA

Facebook

Instagram

YouTube

Twitter

Advertisement

LinkedIn

SIGN UP FOR OUR OTHER NEWSLETTERS

Fox News First

Fox News Opinion

Fox News Lifestyle

Fox News Health

Advertisement

DOWNLOAD OUR APPS

Fox News

FOX Business

Fox Weather

Fox Sports

Tubi

Advertisement

WATCH FOX NEWS ONLINE

Fox News Go

STREAM FOX NATION

Fox Nation

Stay up to date on the latest AI technology advancements and learn about the challenges and opportunities AI presents now and for the future with Fox News here.

Continue Reading

Technology

Microsoft’s Edge Copilot update uses AI to pull information from across your tabs

Published

on

Microsoft’s Edge Copilot update uses AI to pull information from across your tabs

Microsoft Edge is adding a new feature that will allow its Copilot AI chatbot to gather information from all of your open tabs. When you start a conversation with Copilot, you can ask the chatbot questions about what’s in your tabs, compare the products you’re looking at, summarize your open articles, and more.

In its announcement, Microsoft says you can “select which experiences you want or leave off the ones you don’t.” The company is retiring Copilot Mode as well, which could similarly draw information from your tabs but offered some agentic features, like the ability to book a reservation on your behalf. Microsoft has since folded these agentic capabilities into its “Browse with Copilot” tool.

Several other AI features are coming to Edge, including an AI-powered “Study and Learn” mode that can turn the article you’re looking at into a study session or interactive quiz. There’s a new tool that turns your tabs into AI-powered podcasts as well, similar to what you’d find on NotebookLM, and an AI writing assistant that will pop up when you start entering text on a webpage.

You can also give Copilot permission to access your browsing history to provide more “relevant, high-quality answers,” according to Microsoft. Copilot in Edge on desktop and mobile will come with “long-term memory” as well, which can tailor its responses based on your previous conversations. And, when you open up a new tab, you’ll see a redesigned page that combines chat, search, and web navigation, along with the Journeys feature, which uses AI to organize your browsing history into categories that you can revisit.

Meanwhile, an update to Edge’s mobile app will allow you to share your screen with Copilot and talk through the questions about what you’re seeing. Microsoft says you’ll see “clear visual cues” when Copilot is active, “so you know when it’s taking an action, helping, listening, or viewing.”

Advertisement
Continue Reading
Advertisement

Trending