OpenAI Hacked by Researchers Using Claude
- Security startup Hacktron disclosed this week that it used Anthropic's Claude Opus 5 to compromise an OpenAI employee's ChatGPT account by exploiting a vulnerability in the company's community forum.
- Researchers discovered a heap buffer overflow in the forum's libheif image-processing software, which they developed into a functional exploit chain using Claude Opus 5 in less than 72 hours, according to Hacktron.
- After gaining forum access, the team exploited an identity flaw to compromise an employee's Codex account, then used it to generate a benign pull request within OpenAI's internal GitHub repository.
- OpenAI patched the community forum, revoked affected sessions, and paid Hacktron a $6,500 bounty, though the company has not published a detailed account of the incident.
- CEO Zayne Zhang of Hacktron noted that "the worlds of AI safety and cybersecurity are converging," highlighting how AI agents with broad credential access create new attack surfaces across internal infrastructure.
139 Articles
139 Articles
Hackers breached OpenAI, adding to fever pitch of security and safety concerns
A small group of cybersecurity researchers said Sunday that they broke into OpenAI earlier this year, an announcement that has added a new element of alarm around AI security and safety.
(San Francisco = Yonhap News) Correspondent Kwon Young-jeon = A case has been discovered in which competitor OpenAI was hacked using Antropic's artificial intelligence (AI) model, Claude.
Three investigators used Claude to commit OpenAI accounts in less than 72 hours and alert about the new offensive power of AI.
The intrusion, confirmed to the AFP by OpenAI, occurred in the framework of an exercise organized by the company itself in order to identify vulnerabilities in its systems with the help of external computer specialists. The case adds to the growing concern among security experts that AI tools are making it faster and cheaper to carry out sophisticated cyberattacks that previously required specialized teams and months of work. Hacktron researcher…
Hacktron AI researchers violated ChatGPT accounts using Anthropic models. OpenAI corrected the security failure in a few hours.
Meet Harsh Jaiswal, Mohan Pedhapati and Rahul Maini: 3 Indian-origin researchers who used Claude to breach OpenAI systems, won $6,500 bounty
US News: Three Indian-origin cybersecurity researchers, Harsh Jaiswal, Mohan Pedhapati and Rahul Maini, demonstrated how Anthropic's Claude AI could be used to.
Coverage Details
Bias Distribution
- 41% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
