Published • loading... • Updated
OpenAI Hacked by Researchers Using Claude
Hacktron said Claude Opus 5 helped it chain two flaws in less than 72 hours and win a $6,500 bounty from OpenAI.
- 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.
Insights by Ground AI
Podcasts & Opinions
142 Articles
142 Articles
Hacktron researchers used Claude to take advantage of OpenAI's vulnerability by accessing the employee's account and GitHub's corporate account.
·Kyiv, Ukraine
Read Full Article
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.
·New York, United States
Read Full Article
(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.
·Seoul, Korea (the Republic of)
Read Full Article
Three investigators used Claude to commit OpenAI accounts in less than 72 hours and alert about the new offensive power of AI.
·Los Angeles, United States
Read Full ArticleCoverage Details
Total News Sources142
Leaning Left11Leaning Right20Center23Last UpdatedBias Distribution43% Center
Bias Distribution
- 43% of the sources are Center
43% Center
L 20%
C 43%
R 37%
Factuality
To view factuality data please Upgrade to Premium
