search icon
search icon
Flag Arrow Down
Română
Română
Magyar
Magyar
English
English
Français
Français
Deutsch
Deutsch
Italiano
Italiano
Español
Español
Русский
Русский
日本語
日本語
中国人
中国人

Change Language

arrow down
  • Română
    Română
  • Magyar
    Magyar
  • English
    English
  • Français
    Français
  • Deutsch
    Deutsch
  • Italiano
    Italiano
  • Español
    Español
  • Русский
    Русский
  • 日本語
    日本語
  • 中国人
    中国人
Sections
  • News
  • Exclusive
  • INSCOP Surveys
  • Podcast
  • EU
  • Diaspora
  • Republic of Moldova
  • Politics
  • Economy
  • Current Affairs
  • International
  • Sport
  • Health
  • Education
  • IT&C knowledge
  • Arts & Lifestyle
  • Opinions
  • Elections 2025
  • Environment
About Us
Contact
Privacy policy
Terms and conditions
Quickly scroll through news digests and see how they are covered in different publications!
  • News
  • Exclusive
    • INSCOP Surveys
    • Podcast
    • EU
    • Diaspora
    • Republic of Moldova
    • Politics
    • Economy
    • Current Affairs
    • International
    • Sport
    • Health
    • Education
    • IT&C knowledge
    • Arts & Lifestyle
    • Opinions
    • Elections 2025
    • Environment
141 new news items in the last 24 hours
  1. Home
  2. IT&C knowledge

Hacktron AI exploited two ChatGPT vulnerabilities to breach OpenAI’s systems, using the Claude chatbot (Anthropic)

Sanziana Georgescu
whatsapp
facebook
linkedin
x
copy-link copy-link
18 September 2026, 16:31
main event image
IT&C knowledge
Shutterstock
google-preference

Always see our news on Google

Hacktron AI, a U.S. start-up specializing in cybersecurity research, announced Friday that it had compromised the ChatGPT accounts of several OpenAI employees, initially using Anthropic’s Claude chatbot. The attack was carried out as part of OpenAI’s vulnerability disclosure rewards program, and the company paid the researchers $6,500.

The three-person team chained together two critical vulnerabilities. On July 25, the researchers identified a flaw in Discourse, third-party software used for OpenAI’s community forum. After gaining access to the server, they discovered a second vulnerability that allowed them to take control of certain ChatGPT and Codex accounts, including those belonging to OpenAI employees.

One of the compromised accounts had Codex connected to OpenAI’s organization on GitHub, giving the researchers access to the cache of certain software applications and potentially to other internal systems. Hacktron said the Claude model initially used was unable to develop a working exploit, but the situation changed after a new version of the model was released.

OpenAI and Discourse were notified, and Discourse released an update on July 27. OpenAI confirmed that the vulnerabilities had been fixed. The incident adds to a series of security problems and warnings concerning the accelerated development of artificial intelligence systems.

採,

Sources

sursa imagine
Hot News
Cercetătorii au folosit Claude pentru a sparge sistemele OpenAI, profitând de două vulnerabilități critice
sursa imagine
The Guardian EU
OpenAI 'ethically hacked' with help of Anthropic's Claude chatbot

Latest News

11:36

Nicusor Dan says he is afraid of 2028 and calls on Romania to focus on security, education and digitalization

11:35

Nicușor Dan calls for an AI strategy for the Romanian state and the automated processing of documents for the diaspora

11:30

The European Commission was targeted by a cyberattack / Internal applications temporarily disabled

11:30

Romanians who own a single residence could be exempt from the building tax and the tax on the associated land

11:10

The Israeli army launches a new ground operation in an area of Gaza controlled by Hamas

See more news

NEWS ON THE SAME TOPICS

event image
IT&C knowledge
OpenAI reveals troubling incidents: AI models tried to cheat and concealed fabricated information
event image
International
OpenAI has informed more than 100 organizations about incidents involving unauthorized activities by its artificial intelligence agents
event image
International
ChatGPT, Gemini, Claude and Grok experienced outages / Thousands of users reported problems in more than 70 countries
event image
International
OpenAI alerted dozens of institutions after AI agents accessed websites and improperly transferred users’ images
event image
IT&C knowledge
OpenAI suspends the training and evaluation of certain advanced models after AI agents bypassed controls and accessed external systems
event image
IT&C knowledge
OpenAI warns: Cyber attacks with AI are becoming a dangerous reality
app preview
Personalized news feed, AI-powered search, and notifications in a more interactive experience.
app preview app preview
ChatGPT OpenAi GitHub cyber attack codex

Editor’s Recommendations

main event image
INSCOP Surveys
2 hours ago

November 2026: Informat.ro – INSCOP Research BAROMETER, 15th Edition – Chapter X: Temporary Restriction of Access to Online Platforms

main event image
International
36 minutes ago

The historic Trump–Xi–Putin trilateral has begun: “Let’s see if we can achieve something,” says Trump / Why Shenzhen is not Yalta

Sources
imagine sursa
imagine sursa
imagine sursa
main event image
Opinions
44 minutes ago

Andrei Pleșu: What Our Ministers Were and What They Have Become

main event image
Exclusive
1 hour ago

EXCLUSIVE The top domestic political topics trending over the past week / The Lyrica shortage crisis, Marian Neacșu’s new responsibilities, and debates over administrative reform

main event image
Exclusive
1 hour ago
Original Content

November 19, 2026. TV: What was discussed last night on the news television channels

app preview
Personalized news feed, AI-powered search, and notifications in a more interactive experience.
app preview
app store badge google play badge
  • News
  • Exclusive
  • INSCOP Surveys
  • Podcast
  • EU
  • Diaspora
  • Republic of Moldova
  • Politics
  • Economy
  • Current Affairs
  • International
  • Sport
  • Health
  • Education
  • IT&C knowledge
  • Arts & Lifestyle
  • Opinions
  • Elections 2025
  • Environment
  • About Us
  • Contact
Privacy policy
Cookies Policy
Terms and conditions
Open source licenses
All rights reserved Strategic Media Team SRL

Technology in partnership with

anpc-sal anpc-sol