cd /news/ai-safety/researchers-use-claude-to-breach-ope… · home topics ai-safety article
[ARTICLE · art-133800] src=tag24.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Researchers use Claude to breach OpenAI's internal systems, exposing big vulnerability

Security research firm Hacktron said it breached OpenAI's internal systems by exploiting a flaw in OpenAI's public help forum, run on the Discourse platform, and reported the vulnerability to OpenAI and Discourse. OpenAI confirmed the flaw was fixed within about 14 hours of notification and paid the researchers a $6,500 reward, with OpenAI spokesperson Drew Pusateri saying the company narrowed permissions on Community sign-in tokens and revoked affected tokens and sessions. Hacktron said it initially used Anthropic's Claude Opus 4.8 to identify and exploit the flaw but struggled to make it work consistently, and that after Anthropic released Claude Opus 5 the newer model produced a working hack within about three hours; the researchers did not use the restricted Claude Mythos model.

read2 min views1 publishedSep 18, 2026
Researchers use Claude to breach OpenAI's internal systems, exposing big vulnerability
Image: Tag24 (auto-discovered)

Researchers use Claude to breach OpenAI's internal systems, exposing big vulnerability #

Washington DC - A security research company said Friday it managed to break into OpenAI's internal systems using the latest software from Anthropic, exposing how quickly the technology can carry out sophisticated cyberattacks.

The researchers from security firm Hacktron said they found a security flaw in OpenAI's public help forum, run by the Discourse platform, that allowed them to take control of the site.

"We immediately reported the initial vulnerability to OpenAI and Discourse and worked with them to coordinate the patch," Hacktron said in a blog post.

"We appreciate their attention to detail and fast resolution of this issue," the post added.

OpenAI confirmed the flaw was fixed within about 14 hours of being notified and paid the researchers a $6,500 reward.

"We thank the researchers for contacting us and sharing their findings. We narrowed the permissions on Community sign-in tokens and revoked affected tokens and sessions," said Drew Pusateri, an OpenAI spokesperson.

The Hacktron researchers said they initially used Anthropic's Claude Opus 4.8 to identify and exploit the software flaw, but struggled to make it work consistently.

After Anthropic released Claude Opus 5, the researchers said the newer model produced a working hack within about three hours.

The hackers did not use Claude Mythos, a more capable Anthropic model that is restricted to a small group of vetted cyber-defense organizations.

Anthropic has described Mythos as having the strongest cybersecurity capabilities of any model it has built.

Are AI tools making cyberattacks easier?

Hacktron said the underlying software flaw is not unique to OpenAI and is used across many companies' products, including those made by Slack and Meta.

The firm said it is continuing similar tests at other companies.

The case adds to growing concern among security experts that AI tools are making it faster and cheaper to carry out sophisticated cyberattacks that once required specialized teams and months of work.

Cover photo: IMAGO / ZUMA Press Wire

── more in #ai-safety 4 stories · sorted by recency
── more on @hacktron 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/researchers-use-clau…] indexed:0 read:2min 2026-09-18 ·