Security Researchers Hacked Into OpenAI Using Anthropic’s Claude

CB News
4 followers
3 Video Views·Sep 19, 2026
A group of cybersecurity researchers managed to breach OpenAI’s internal system using rival Anthropic’s Claude AI software as part of a bug bounty program, highlighting the growing threats posed by advanced AI models amid broader safety warnings about the technology from top industry executives and researchers.
AI Generated·May contain errors
A group of cybersecurity researchers breached OpenAI's internal system
using rival Anthropics' Claude AI software as part of a bug bounty program, highlighting the growing
threats posed by advanced AI models amid broader safety warnings about the technology from industry
insiders. Researchers at the security startup Hacktron AI said they gained access to an OpenAI
employee's ChatGPT account, which then gave them access to the company's internal code on GitHub.
The Wall Street Journal first reported the incident, noting the team was participating
in an OpenAI bug-hunting program and that the company paid the researchers a $6,500 bounty
for disclosing their work. In its report of the incident, Hacktron said they first tried to use
Anthropics' Claude Opus 4.8 to attempt the breach, but it struggled across several sessions to
produce a working exploit. However, once Anthropics launched Opus 5, they tried again and succeeded,
and noted that every new model is getting increasingly capable.
According to the journal, the researchers had access to a special version of Claude,
which has been made available to qualified cybersecurity practitioners.
In a statement to Forbes, OpenAI spokesperson Drew Pusateri said the company thanked the
researchers for contacting us and sharing their findings, and said it had resolved the vulnerability.
In their report, the researchers said the OpenAI hack took only a few days for an agent
and just a few hours of human time to pull off. The breach was part of HEIF Heist,
a broader research project into the vulnerability of how many software and services process certain
image files. This exploit has been able to find vulnerabilities with Slack, Zoom,
Meta and others, and only took two months, three researchers, and cost less than $3,000
in tokens in total. In their conclusion note, the researchers wrote,
Software has long benefited from a kind of security through complexity.
AI is removing that protection and turning more of this scarce expertise into compute.
Work that was once required a well-resourced team and months of effort can now be compressed
into days. Security assumptions must catch up with attacker capabilities.
For more on this story, click the link in the description.
