Security researchers use Claude to hack into OpenAI
publishers 2articles 2first reported 18 Sep, 13:30 UTCdeveloping since 18 Sep · 3 editions
A team of three independent security researchers, part of the group Hacktron, reportedly used Anthropic's Claude Opus 4.8 and 5 to gain unauthorized access to OpenAI employee accounts within less than 72 hours, according to The Wall Street Journal, as reported by The Verge. The researchers were able to access OpenAI's GitHub repository, known as 'Monorepo,' which is said to contain 'OpenAI's algorithmic secrets.'
According to Ars Technica, the researchers used Claude to reach an OpenAI employee account and access sensitive GitHub data. The incident highlights potential vulnerabilities in OpenAI's security measures and raises concerns about the use of AI tools in cyberattacks. OpenAI has not yet publicly commented on the breach.
The details of how exactly the researchers exploited Claude's capabilities remain unclear, and no specific quotes from the researchers were provided in the sources. The findings underscore the growing risks associated with the use of advanced AI models in security-related activities.
HOW THIS STORY WAS MADE
Written from 2 articles, 2 with the publisher's own text; 2 independent newsrooms once syndicated copies count as one.
- Publishers
- 2
- Source articles
- 2
- Given to the writer
- 2, 2 with the article's own text
- Independent newsrooms
- 2
- Publication gate
- passed
- Human review
- none
Written by a language model from the sources above, then checked by a second model that may only cut, attribute or correct. How it works →