ChatGPT

Chrome, Edge Extensions Caught Stealing ChatGPT Sessions

Artificial Intelligence, browser extension, ChatGPT, Chrome, extension, Malware & Threats /

Chrome, Edge Extensions Caught Stealing ChatGPT Sessions 2026-01-27 at 15:49 By Ionut Arghire Marketed as ChatGPT enhancement and productivity tools, the extensions allow the threat actor to access the victim’s ChatGPT data. The post Chrome, Edge Extensions Caught Stealing ChatGPT Sessions appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source […]

React to this headline:

Loading spinner

Chrome, Edge Extensions Caught Stealing ChatGPT Sessions Read More »

OpenAI adds age prediction to ChatGPT to strengthen teen safety

ChatGPT, Data Protection, News, OpenAI /

OpenAI adds age prediction to ChatGPT to strengthen teen safety 2026-01-21 at 15:05 By Sinisa Markovic OpenAI is rolling out age prediction on ChatGPT consumer plans to help determine whether an account likely belongs to someone under 18. Age prediction builds on protections already in place. ChatGPT relies on an age prediction model that evaluates

React to this headline:

Loading spinner

OpenAI adds age prediction to ChatGPT to strengthen teen safety Read More »

‘ZombieAgent’ Attack Let Researchers Take Over ChatGPT

AI, AI hack, Artificial Intelligence, ChatGPT, ZombieAgent /

‘ZombieAgent’ Attack Let Researchers Take Over ChatGPT 2026-01-09 at 14:47 By Ionut Arghire Radware bypassed ChatGPT’s protections to exfiltrate user data and implant a persistent logic into the agent’s long-term memory. The post ‘ZombieAgent’ Attack Let Researchers Take Over ChatGPT appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source React

React to this headline:

Loading spinner

‘ZombieAgent’ Attack Let Researchers Take Over ChatGPT Read More »

ChatGPT Vulnerability Exposed Underlying Cloud Infrastructure

AI, Artificial Intelligence, ChatGPT, OpenAI, SSRF, vulnerability /

ChatGPT Vulnerability Exposed Underlying Cloud Infrastructure 2025-11-13 at 17:50 By Eduard Kovacs A researcher found a way to exploit an SSRF vulnerability related to custom GPTs to obtain an Azure access token.  The post ChatGPT Vulnerability Exposed Underlying Cloud Infrastructure appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source React

React to this headline:

Loading spinner

ChatGPT Vulnerability Exposed Underlying Cloud Infrastructure Read More »

Researchers Hack ChatGPT Memories and Web Search Features

AI, AI jailbreak, Artificial Intelligence, ChatGPT, Featured /

Researchers Hack ChatGPT Memories and Web Search Features 2025-11-06 at 19:09 By Eduard Kovacs Tenable researchers discovered seven vulnerabilities, including ones affecting the latest GPT model. The post Researchers Hack ChatGPT Memories and Web Search Features appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source React to this headline:

React to this headline:

Loading spinner

Researchers Hack ChatGPT Memories and Web Search Features Read More »

AI chatbots are sliding toward a privacy crisis

Artificial Intelligence, ChatGPT, CISO, cyber risk, cybersecurity, Don't miss, Features, generative AI, Harmonic, Ivanti, LLMs, News, OpenAI, Privacy, Tanium /

AI chatbots are sliding toward a privacy crisis 2025-10-31 at 09:00 By Sinisa Markovic AI chat tools are taking over offices, but at what cost to privacy? People often feel anonymous in chat interfaces and may share personal data without realizing the risks. Cybercriminals see the same opening, and it may only be a matter

React to this headline:

Loading spinner

AI chatbots are sliding toward a privacy crisis Read More »

OpenAI Atlas Omnibox Is Vulnerable to Jailbreaks

Artificial Intelligence, ChatGPT, jailbreak, OpenAI, Vulnerabilities, vulnerability /

OpenAI Atlas Omnibox Is Vulnerable to Jailbreaks 2025-10-25 at 23:58 By Kevin Townsend Researchers have discovered that a prompt can be disguised as an url, and accepted by Atlas as an url in the omnibox. The post OpenAI Atlas Omnibox Is Vulnerable to Jailbreaks appeared first on SecurityWeek. This article is an excerpt from SecurityWeek

React to this headline:

Loading spinner

OpenAI Atlas Omnibox Is Vulnerable to Jailbreaks Read More »

ChatGPT Tricked Into Solving CAPTCHAs

AI, AI jailbreak, Artificial Intelligence, CAPTCHA, ChatGPT /

ChatGPT Tricked Into Solving CAPTCHAs 2025-09-19 at 14:30 By Ionut Arghire The AI agent was able to solve different types of CAPTCHAs and adjusted its cursor movements to better mimic human behavior. The post ChatGPT Tricked Into Solving CAPTCHAs appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source React to

React to this headline:

Loading spinner

ChatGPT Tricked Into Solving CAPTCHAs Read More »

ChatGPT Targeted in Server-Side Data Theft Attack

AI, Artificial Intelligence, ChatGPT, data theft, Deep Research, Featured, server side, ShadowLeak /

ChatGPT Targeted in Server-Side Data Theft Attack 2025-09-18 at 18:49 By Eduard Kovacs OpenAI has fixed this zero-click attack method called by researchers ShadowLeak. The post ChatGPT Targeted in Server-Side Data Theft Attack appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source React to this headline:

React to this headline:

Loading spinner

ChatGPT Targeted in Server-Side Data Theft Attack Read More »

ChatGPT’s New Calendar Integration Can Be Abused to Steal Emails

AI, Artificial Intelligence, calendar, ChatGPT, Featured, integration /

ChatGPT’s New Calendar Integration Can Be Abused to Steal Emails 2025-09-16 at 14:05 By Eduard Kovacs EdisonWatch researchers demonstrated the new hack after OpenAI added support for MCP tools in ChatGPT. The post ChatGPT’s New Calendar Integration Can Be Abused to Steal Emails appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View

React to this headline:

Loading spinner

ChatGPT’s New Calendar Integration Can Be Abused to Steal Emails Read More »

Most enterprise AI use is invisible to security teams

Artificial Intelligence, ChatGPT, Don't miss, enterprise, Features, Lanai, News /

Most enterprise AI use is invisible to security teams 2025-09-15 at 10:38 By Mirko Zorz Most enterprise AI activity is happening without the knowledge of IT and security teams. According to Lanai, 89% of AI use inside organizations goes unseen, creating risks around data privacy, compliance, and governance. This blind spot is growing as AI

React to this headline:

Loading spinner

Most enterprise AI use is invisible to security teams Read More »

GPT-5 Has a Vulnerability: Its Router Can Send You to Older, Less Safe Models

Artificial Intelligence, ChatGPT, Featured, jailbreak /

GPT-5 Has a Vulnerability: Its Router Can Send You to Older, Less Safe Models 2025-08-20 at 17:52 By Kevin Townsend Instead of GPT-5 Pro, your query could be quietly redirected to an older, weaker model, opening the door to jailbreaks, hallucinations, and unsafe outputs. The post GPT-5 Has a Vulnerability: Its Router Can Send You

React to this headline:

Loading spinner

GPT-5 Has a Vulnerability: Its Router Can Send You to Older, Less Safe Models Read More »

Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise

AI, Artificial Intelligence, ChatGPT, Featured, jailbreak, OpenAI /

Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise 2025-08-08 at 21:34 By Kevin Townsend Researchers demonstrate how multi-turn “storytelling” attacks bypass prompt-level filters, exposing systemic weaknesses in GPT-5’s defenses. The post Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise appeared first on SecurityWeek. This article is an

React to this headline:

Loading spinner

Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise Read More »

What GPT‑5 means for IT teams, devs, and the future of AI at work

Artificial Intelligence, Azoma, ChatGPT, Don't miss, generative AI, LLMs, News /

What GPT‑5 means for IT teams, devs, and the future of AI at work 2025-08-07 at 20:58 By Sinisa Markovic OpenAI has released GPT‑5, the newest version of its large language model. It’s now available to developers and ChatGPT users, and it brings some real changes to how AI can be used in business and

React to this headline:

Loading spinner

What GPT‑5 means for IT teams, devs, and the future of AI at work Read More »

Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation

AI, Artificial Intelligence, ChatGPT, Copilot, Cursor, Data Exposure, Gemini /

Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation 2025-08-07 at 02:36 By Eduard Kovacs Zenity has shown how AI assistants such as ChatGPT, Copilot, Cursor, Gemini, and Salesforce Einstein can be abused using specially crafted prompts. The post Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation appeared first on

React to this headline:

Loading spinner

Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation Read More »

Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data 

AI, Artificial Intelligence, browser extension, ChatGPT, Gemini, Man-in-the-Prompt /

Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data  2025-07-31 at 15:07 By Eduard Kovacs LayerX has disclosed an AI chatbot hacking method via web browser extensions it has named ‘man-in-the-prompt’. The post Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data  appeared first on SecurityWeek. This article is an excerpt

React to this headline:

Loading spinner

Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data  Read More »

Can ChatGPT predict Bitcoin’s next move?

ChatGPT /

Can ChatGPT predict Bitcoin’s next move? 2025-07-04 at 19:02 By Cointelegraph by Bradley Peak While it’s not built for real-time calls, ChatGPT can still support smarter Bitcoin trading decisions when paired with the right data and well-crafted prompts. This article is an excerpt from Cointelegraph.com News View Original Source React to this headline:

React to this headline:

Loading spinner

Can ChatGPT predict Bitcoin’s next move? Read More »

Users lack control as major AI platforms share personal info with third parties

ChatGPT, cybersecurity, generative AI, Incogni, LLMs, Meta, Microsoft, News, Privacy, report /

Users lack control as major AI platforms share personal info with third parties 2025-06-25 at 07:02 By Help Net Security Some of the most popular generative AI and large language model (LLM) platforms, from companies like Meta, Google, and Microsoft, are collecting sensitive data and sharing it with unknown third parties, leaving users with limited

React to this headline:

Loading spinner

Users lack control as major AI platforms share personal info with third parties Read More »

86% of all LLM usage is driven by ChatGPT

Artificial Intelligence, ChatGPT, cybersecurity, LLMs, New Relic, News, report /

86% of all LLM usage is driven by ChatGPT 2025-06-11 at 07:01 By Help Net Security ChatGPT remains the most widely used LLM among New Relic customers, making up over 86% of all tokens processed. Developers and enterprises are shifting to OpenAI’s latest models, such as GPT-4o and GPT-4o mini, even when more affordable alternatives

React to this headline:

Loading spinner

86% of all LLM usage is driven by ChatGPT Read More »

OpenAI Offering $100K Bounties for Critical Vulnerabilities

Artificial Intelligence, bug bounty program, ChatGPT, OpenAI, SpecterOps, Vulnerabilities /

OpenAI Offering $100K Bounties for Critical Vulnerabilities 2025-03-26 at 22:05 By Ryan Naraine OpenAI has raised its maximum bug bounty payout to $100,000 (up from $20,000) for high-impact flaws in its infrastructure and products. The post OpenAI Offering $100K Bounties for Critical Vulnerabilities appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View

React to this headline:

Loading spinner

OpenAI Offering $100K Bounties for Critical Vulnerabilities Read More »

Scroll to Top