Technology
OpenAI admits AI browsers face unsolvable prompt attacks
NEWYou can now listen to Fox News articles!
Cybercriminals don’t always need malware or exploits to break into systems anymore. Sometimes, they just need the right words in the right place. OpenAI is now openly acknowledging that reality. The company says prompt injection attacks against artificial intelligence (AI)-powered browsers are not a bug that can be fully patched, but a long-term risk that comes with letting AI agents roam the open web. This raises uncomfortable questions about how safe these tools really are, especially as they gain more autonomy and access to your data.
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.
NEW MALWARE CAN READ YOUR CHATS AND STEAL YOUR MONEY
AI-powered browsers can read and act on web content, which also makes them vulnerable to hidden instructions attackers can slip into pages or documents. (Kurt “CyberGuy” Knutsson)
Why prompt injection isn’t going away
In a recent blog post, OpenAI admitted that prompt injection attacks are unlikely to ever be completely eliminated. Prompt injection works by hiding instructions inside web pages, documents or emails in ways that humans don’t notice, but AI agents do. Once the AI reads that content, it can be tricked into following malicious instructions.
OpenAI compared this problem to scams and social engineering. You can reduce them, but you can’t make them disappear. The company also acknowledged that “agent mode” in its ChatGPT Atlas browser increases risk because it expands the attack surface. The more an AI can do on your behalf, the more damage it can cause when something goes wrong.
OpenAI launched the ChatGPT Atlas browser in October, and security researchers immediately started testing its limits. Within hours, demos appeared showing that a few carefully placed words inside a Google Doc could influence how the browser behaved. That same day, Brave published its own warning, explaining that indirect prompt injection is a structural problem for AI-powered browsers, including tools like Perplexity’s Comet.
This isn’t just OpenAI’s problem. Earlier this month, the National Cyber Security Centre in the U.K. warned that prompt injection attacks against generative AI systems may never be fully mitigated.
FAKE AI CHAT RESULTS ARE SPREADING DANGEROUS MAC MALWARE
Prompt injection attacks exploit trust at scale, allowing malicious instructions to influence what an AI agent does without the user ever seeing it. (Kurt “CyberGuy” Knutsson)
The risk trade-off with AI browsers
OpenAI says it views prompt injection as a long-term security challenge that requires constant pressure, not a one-time fix. Its approach relies on faster patch cycles, continuous testing, and layered defenses. That puts it broadly in line with rivals like Anthropic and Google, which have both argued that agentic systems need architectural controls and ongoing stress testing.
Where OpenAI is taking a different approach is with something it calls an “LLM-based automated attacker.” In simple terms, OpenAI trained an AI to act like a hacker. Using reinforcement learning, this attacker bot looks for ways to sneak malicious instructions into an AI agent’s workflow.
The bot runs attacks in simulation first. It predicts how the target AI would reason, what steps it would take and where it might fail. Based on that feedback, it refines the attack and tries again. Because this system has insight into the AI’s internal decision-making, OpenAI believes it can surface weaknesses faster than real-world attackers.
Even with these defenses, AI browsers aren’t safe. They combine two things attackers love: autonomy and access. Unlike regular browsers, they don’t just display information, but also read emails, scan documents, click links and take actions on your behalf. That means a single malicious prompt hidden in a webpage, document or message can influence what the AI does without you ever seeing it. Even when safeguards are in place, these agents operate by trusting content at scale, and that trust can be manipulated.
THIRD-PARTY BREACH EXPOSES CHATGPT ACCOUNT DETAILS
As AI browsers gain more autonomy and access to personal data, limiting permissions and keeping human confirmation in the loop becomes critical for safety. (Kurt “CyberGuy” Knutsson)
7 steps you can take to reduce risk with AI browsers
You may not be able to eliminate prompt injection attacks, but you can significantly limit their impact by changing how you use AI tools.
1) Limit what the AI browser can access
Only give an AI browser access to what it absolutely needs. Avoid connecting your primary email account, cloud storage or payment methods unless there’s a clear reason. The more data an AI can see, the more valuable it becomes to attackers. Limiting access reduces the blast radius if something goes wrong.
2) Require confirmation for every sensitive action
Never allow an AI browser to send emails, make purchases or modify account settings without asking you first. Confirmation breaks long attack chains and gives you a moment to spot suspicious behavior. Many prompt injection attacks rely on the AI acting quietly in the background without user review.
3) Use a password manager for all accounts
A password manager ensures every account has a unique, strong password. If an AI browser or malicious page leaks one credential, attackers can’t reuse it elsewhere. Many password managers also refuse to autofill on unfamiliar or suspicious sites, which can alert you that something isn’t right before you manually enter anything.
Next, see if your email has been exposed in past breaches. Our #1 password manager (see Cyberguy.com) pick includes a built-in breach scanner that checks whether your email address or passwords have appeared in known leaks. If you discover a match, immediately change any reused passwords and secure those accounts with new, unique credentials.
Check out the best expert-reviewed password managers of 2025 at Cyberguy.com
4) Run strong antivirus software on your device
Even if an attack starts inside the browser, antivirus software can still detect suspicious scripts, unauthorized system changes or malicious network activity. Strong antivirus software focuses on behavior, not just files, which is critical when dealing with AI-driven or script-based attacks.
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 & iOS devices at Cyberguy.com
5) Avoid broad or open-ended instructions
Telling an AI browser to “handle whatever is needed” gives attackers room to manipulate it through hidden prompts. Be specific about what the AI is allowed to do and what it should never do. Narrow instructions make it harder for malicious content to influence the agent.
6) Be careful with AI summaries and automated scans
When an AI browser scans emails, documents or web pages for you, remember that hidden instructions can live inside that content. Treat AI-generated actions as drafts or suggestions, not final decisions. Review anything the AI plans to act on before approving it.
7) Keep your browser, AI tools and operating system updated
Security fixes for AI browsers evolve quickly as new attack techniques emerge. Delaying updates leaves known weaknesses open longer than necessary. Turning on automatic updates ensures you get protection as soon as they’re available, even if you miss the announcement.
CLICK HERE TO DOWNLOAD THE FOX NEWS APP
Kurt’s key takeaway
There’s been a meteoric rise in AI browsers. We’re now seeing them from major tech companies, including OpenAI’s Atlas, The Browser Company’s Dia, and Perplexity’s Comet. Even existing browsers like Chrome and Edge are pushing hard to add AI and agentic features into their current infrastructure. While these browsers can be useful, the technology is still early. It’s best not to fall for the hype and to wait for it to mature.
Do you think AI browsers are worth the risk today, or are they moving faster than security can keep up? 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.
Technology
Dyson’s powerful 360 Vis Nav robovac is down to $279.99 for a limited time
If you’re tired of running your vacuum multiple times just to get the dirt and debris out of the carpets in your living room, Dyson’s 360 Vis Nav is worth a look. It’s one of the more powerful robot vacuums currently available, and now through May 11th (or while supplies last), it’s on sale at Woot for an all-time low of $279.99 ($919 off) with a full two-year warranty.
The last-gen 360 Vis Nav offers a whopping 65 air watts of suction, allowing it to pull dirt, dust, and pet hair from carpets impressively well. In her brief time testing the robovac, my colleague Jennifer Pattison Tuohy said the Dyson “demolished a pile of dry oatmeal in seconds,” adding that she briefly worried it might even suck up the tassels on her large rug (it didn’t). By comparison, many robot vacuums — including Dyson’s new $1,200 Spot + Scrub AI — require multiple passes to fully eradicate the same kind of mess on your floor.
What’s more, the robovac’s small, D-shaped design and the location of its ultra-fluffy brush allow it to dig into edges and corners more effectively than many of the more roundish robot vacuums, while its lower profile lets it easily get under most beds and sofas. The roomy 500ml dustbin also means you likely won’t need to empty it too often, while Dyson’s built-in handle and terrific quick-release button make removing said bin a relatively simple task when it’s time to do so.
While it is undeniably powerful, it’s worth noting that the 360 Vis Nav lacks a few features found on some of its more modern rivals. Although its navigation worked well enough during our testing, it lacks AI-powered obstacle avoidance and doesn’t come with a self-emptying dock. Battery life is also relatively short at around 65 minutes per charge. Nonetheless, if your top priority is quickly removing dust, dirt, and pet hair from carpets without multiple passes, the Dyson remains an option worth considering, especially at this discounted price.
Technology
Global scam crackdown leads to 276 arrests
NEWYou can now listen to Fox News articles!
We’ve often warned you about romance scams and crypto “investment” opportunities that feel too good to pass up. Now, there’s a major update that shows just how organized these operations have become.
The Department of Justice and Federal Bureau of Investigation announced a sweeping international operation that led to at least 276 arrests and the shutdown of multiple scam centers tied to cryptocurrency fraud. These networks targeted Americans and drained millions of dollars from victims.
The operation spanned continents and involved coordinated efforts by law enforcement and tech companies.
Sign up for my FREE CyberGuy Report
- Get my best tech tips, urgent security alerts and exclusive deals delivered straight to your inbox.
- For simple, real-world ways to spot scams early and stay protected, visit CyberGuy.com – trusted by millions who watch CyberGuy on TV daily.
- Plus, you’ll get instant access to my Ultimate Scam Survival Guide free when you join.
TOP 5 SCAMS SPREADING RIGHT NOW
The Department of Justice and FBI say international scam networks used romance and fake crypto investment schemes to steal millions from victims. (Helena Dolderer/Picture Alliance)
How the cryptocurrency scam crackdown unfolded
Authorities worked with partners around the world, including the Dubai Police and law enforcement agencies in Thailand and beyond. Together, they dismantled at least nine scam centers linked to large-scale crypto fraud.
Several suspects now face federal charges in the United States, including wire fraud and money laundering. Investigators say these operations functioned like businesses, with recruitment, management layers and structured systems designed to deceive victims.
Officials made it clear that this effort sends a message. Fraud crosses borders, and enforcement is now doing the same.
How crypto investment scams target victims
These schemes often follow a pattern known as “pig-butchering.” It is a slow, calculated tactic that builds trust before any money is involved.
A scammer may reach out through social media or a messaging app and start a casual conversation. Over time, that interaction turns more personal. In some cases, it feels like a real relationship. Once trust is established, the topic shifts toward investing, often framed as a unique crypto opportunity.
Victims are guided through setting up accounts and transferring funds to platforms that appear legitimate. The dashboards may even show fake gains to build confidence. At that point, control of the money is already gone. Funds are quickly moved through multiple accounts and eventually end up with the scammers.
Many victims are encouraged to keep going, sometimes borrowing money or taking out loans to invest more. By the time the truth becomes clear, the losses can be devastating.
How Meta Platforms, Inc. helped track scam networks
Meta Platforms, Inc. played a key role in the investigation by providing data that helped law enforcement identify and track these networks.
The company says it has taken aggressive action across its platforms. In 2025 alone, Meta removed more than 159 million scam ads and shut down 10.9 million accounts linked to scam centers. More recently, it disabled over 150,000 accounts connected to these networks as part of a coordinated enforcement effort.
“Meta is committed to combatting online fraud and scams, and we are proud to partner with law enforcement in these efforts,” Chris Sonderby, Meta’s vice president and deputy general counsel, said. “We applaud the DOJ and FBI for their leadership in holding criminal scammers accountable and protecting American consumers.”
FROM FRIENDLY TEXT TO FINANCIAL TRAP: THE NEW SCAM TREND
Federal authorities announced a sweeping international crackdown that led to at least 276 arrests tied to cryptocurrency scam centers targeting Americans. (Kurt “CyberGuy” Knutsson)
New tools to stop cryptocurrency scams in real time
Meta is also rolling out new protections across its apps to help users spot scams before they get pulled in.
On Facebook, users may see alerts tied to suspicious friend requests, especially when an account shows unusual behavior such as limited connections or inconsistent location details.
On WhatsApp, new warnings are designed to prevent scammers from linking their own devices to someone else’s account, giving users a chance to pause before approving a risky request.
Messenger is also expanding its scam detection tools. When a conversation shows patterns linked to common fraud tactics, users may receive prompts that explain the risk and suggest actions like blocking or reporting the account.
Why this cryptocurrency scam crackdown matters to you
This operation highlights how organized these scam networks have become. These are not random messages from a single person. They are coordinated groups running structured operations designed to build trust, create urgency and move money quickly.
Even with hundreds of arrests, the threat remains. New networks continue to emerge, often using the same playbook with slight changes. That means staying informed is still one of the most effective ways to protect yourself.
Ways to stay safe from cryptocurrency scams
Scammers follow familiar patterns, which means there are clear warning signs you can watch for and simple steps you can take to protect yourself.
1) Slow down unexpected connections
If someone you do not know reaches out and quickly builds a personal connection, slow things down and question the situation. Scammers rely on momentum, so taking a pause can help you spot inconsistencies.
2) Verify investment platforms before sending money
Before sending money to any investment platform, take time to verify that it is legitimate. A professional-looking website or app does not guarantee it is real. Look for independent reviews and official registration details.
3) Avoid sending crypto to unknown sources
Avoid sending cryptocurrency to individuals or platforms you cannot confirm. Once those transactions go through, they are extremely difficult to recover.
4) Watch for pressure and urgency
Be aware of pressure. If someone pushes you to act quickly or invest more, that urgency is often a warning sign.
5) Use strong antivirus protection
Strong antivirus software can help block malicious links, fake investment sites and other threats before they reach you, adding another layer of defense against scam attempts. Get my picks for the best 2026 antivirus protection winners for your Windows, Mac, Android and iOS devices at Cyberguy.com.
THE ONE THING SCAMMERS CHECK BEFORE TARGETING YOU ONLINE
Meta said it removed more than 159 million scam ads in 2025 and helped investigators track networks tied to cryptocurrency fraud. (Halfpoint/Getty Images)
6) Limit your personal data exposure
Scammers often rely on publicly available information to build trust. Reducing how much of your personal data appears online by using a data removal service can make it harder for them to target you in the first place. 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.
7) Strengthen your account security
It also helps to strengthen your digital security. Enable two-factor authentication (2FA) on your accounts and use trusted security tools to reduce exposure to malicious links and messages.
8) Report scams as soon as possible
If you believe you have been targeted or defrauded, report it to the FBI’s Internet Crime Complaint Center at ic3.gov as soon as possible.
Kurt’s key takeaways
This global crackdown is a meaningful step forward. It shows what can happen when law enforcement, tech companies and international partners work together. At the same time, these scams are not going away. The tactics will continue to evolve, and new networks will take the place of those that were shut down. Awareness and caution remain your strongest defenses.
CLICK HERE TO DOWNLOAD THE FOX NEWS APP
We report a lot about scams but not so much about scammers getting caught. Does this make you feel like real progress is being made in stopping them? 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.
- For simple, real-world ways to spot scams early and stay protected, visit CyberGuy.com – trusted by millions who watch CyberGuy on TV daily.
- Plus, you’ll get instant access to my Ultimate Scam Survival Guide free when you join.
Copyright 2026 CyberGuy.com. All rights reserved.
Technology
Asus chases Elgato with its own secondary touchscreen display
Asus’s latest gaming monitor is a little smaller than usual. The ROG Strix XG129C, announced on Friday, is a 12.3-inch touchscreen IPS display that’s intended to be a sidekick for a larger main monitor, similar to the 14.1-inch secondary display in the 2020 Asus ROG Zephyrus Duo 15. It’s a slightly smaller competitor to Corsair’s Xeneon Edge, which has a 14.5-inch display, but the same 720p resolution.
Asus says the XG129C covers 125 percent of the sRGB color gamut and 90 percent of the DCI-P3 color gamut. It also comes with a one-year subscription for the hardware monitoring tool AIDA64 Extreme, which would usually cost $65. Besides acting as a performance monitor for your PC, sidekick displays like this can also be handy as an extension for streaming or editing setups, much like Elgato’s Stream Deck.
Along with the little XG129C, Asus also announced the ROG Strix OLED XG34WCDMS, a 34-inch RGB Tandem QD-OLED gaming monitor. It features a 280Hz refresh rate and a 3440 x 1440p resolution, and, according to Asus, covers 99 percent of the DCI-P3 color gamut. Asus has not yet officially announced pricing for either display.
-
Minneapolis, MN3 minutes agoINTERVIEW: Doors Open Minneapolis
-
Indianapolis, IN9 minutes agoIndianapolis Race Results: May 9, 2026 (INDYCAR) – Racing News
-
Pittsburg, PA15 minutes agoHornets Fall in MIAA Tournament Title Match to #5 Pittsburg State
-
Augusta, GA21 minutes agoHistoric Masters landmark purchased and renovated by local resident
-
Washington, D.C27 minutes agoCandidates for mayor and D.C. congressional delegate outline vision for District’s future
-
Cleveland, OH33 minutes agoUSS Cleveland arrives in namesake city for commissioning
-
Austin, TX39 minutes agoAPD responds to barricaded subject in E Austin
-
Alabama45 minutes agoAlabama softball vs Texas today: recap, score and highlights