cd /news/large-language-models/chatgpt-blindly-trusts-browser-conte… · home topics large-language-models article
[ARTICLE · art-17543] src=theregister.com pub= topic=large-language-models verified=true sentiment=↓ negative

ChatGPT blindly trusts browser content, turning the page into a payload

ChatGPT's blind trust in browser content allows attackers to weaponize web pages as payloads for phishing and data theft. The AI model processes and acts on visible text without verifying its source, enabling malicious actors to craft pages that trick the chatbot into executing harmful actions. This vulnerability turns any browser session into a potential attack vector, exposing users to credential theft and unauthorized data access.

read4 min publishedMay 29, 2026

MOST POPULAR

EVENTS #

Overcoming the trade-offs in data sovereignty

What does data sovereignty actually mean for your network, which trade-offs are unavoidable? Learn more.

From Prompt to Exploit: How LLMs Are Changing API Attacks

Modern applications are API-driven, interconnected, and often over-permissioned, making them an ideal target for AI-assisted attacks.

Architecting the Future: Unlocking Enterprise Data Services for Kubernetes

Join us to discover how to eliminate infrastructure silos and establish a standardized, enterprise-grade cloud-native platform.

Catch the Advanced Attacks Microsoft 365 Misses with Behavioral AI Security

Microsoft 365 is the backbone of enterprise communication, and its native security filters out the known and the noisy.

Virtual Cyber Recovery Sim

Step into the chaos of a live ransomware breach, test your response skills, and team up with other IT and security pros to outsmart cybercriminals

Virtual Cyber Recovery Simulation

Ransomware attacks aren’t slowing down, and neither are we. Druva’s hit event, Escape Ransomware, is now fully virtual.

Agentic AI at Scale: From Pilot to Production

Join us to learn how to unlock real ROI by driving adoption of AI at scale.

AI #

Security

ChatGPT blindly trusts browser content, turning the page into a payload

You and me go ChatGPhish-ing in the dark

Research

Russia-linked threat group put ChatGPT to work from lure to payload

Researchers say 'GREYVIBE' crew used AI tools throughout a campaign targeting Ukrainian military and government

Science

Blue Origin's New Glenn makes a crater-sized dent in Artemis plans

Explosion wrecks rocket and pad, leaving NASA's lunar ambitions looking less than launch-ready

Cyber-Crime

ShinyHunters adds Charter to trophy shelf after 4.9M customer records leak

Telco giant says no sensitive data was taken, though names, addresses, phones, and emails are now out there

Software

That an app 'Fits on a Floppy' is still a useful measure in 2026

In a world of mass-produced bot-slopware, small is more beautiful than ever

Infosec #

Security

ChatGPT blindly trusts browser content, turning the page into a payload

You and me go ChatGPhish-ing in the dark

Research

Russia-linked threat group put ChatGPT to work from lure to payload

Researchers say 'GREYVIBE' crew used AI tools throughout a campaign targeting Ukrainian military and government

Science

Blue Origin's New Glenn makes a crater-sized dent in Artemis plans

Explosion wrecks rocket and pad, leaving NASA's lunar ambitions looking less than launch-ready

Cyber-Crime

ShinyHunters adds Charter to trophy shelf after 4.9M customer records leak

Telco giant says no sensitive data was taken, though names, addresses, phones, and emails are now out there

Software

That an app 'Fits on a Floppy' is still a useful measure in 2026

In a world of mass-produced bot-slopware, small is more beautiful than ever

FOSS #

ChatGPT blindly trusts browser content, turning the page into a payload

You and me go ChatGPhish-ing in the dark

Russia-linked threat group put ChatGPT to work from lure to payload

Researchers say 'GREYVIBE' crew used AI tools throughout a campaign targeting Ukrainian military and government

Blue Origin's New Glenn makes a crater-sized dent in Artemis plans

Explosion wrecks rocket and pad, leaving NASA's lunar ambitions looking less than launch-ready

ShinyHunters adds Charter to trophy shelf after 4.9M customer records leak

Telco giant says no sensitive data was taken, though names, addresses, phones, and emails are now out there

That an app 'Fits on a Floppy' is still a useful measure in 2026

In a world of mass-produced bot-slopware, small is more beautiful than ever

Jammin' on UK defence secretary's jet as Russia blamed for GPS interference

Estonian academic fingers mobile tower-mounted devices as Kremlin tries to swat Ukrainian forces

FEATURES

Europe built sovereign clouds to escape US control. Then forgot about the processors

Nobody believes the 'criminals and scumbags' who hacked Canvas really deleted stolen student data

Europe wants out from under US tech – but first it has to find the exits

GNOME may rule Ubuntu Resolute Raccoon, but X.org isn't roadkill yet

OpenClaw, but in containers: Meet NanoClaw

Open source registries don't have enough money to implement basic security

Contain your Windows apps inside Linux Windows

The Linux mid-life crisis that's an opportunity for Tux-led transformation

Too much AI for some, too little for others: Why AMD can't win with investors

How agentic AI can strain modern memory hierarchies

── more in #large-language-models 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/chatgpt-blindly-trus…] indexed:0 read:4min 2026-05-29 ·