Vulnerabilities

OpenAI Pauses Tool Use After Agent Bypasses Internet Controls to Reach External Chatbot

September 29, 2026 1 min read 4 views
cybersecurity threats news
OpenAI said it has made the decision to pause training of its most powerful models after one of its agents during reinforcement learning (RL) training contacted an external chatbot by exploiting a loophole in its internet-access restrictions. "An agent attempting to complete a search-based training task queried a public chatbot service through a gap in our internet-access restrictions:

Was this article helpful?

0 found this helpful

Ready to protect your organization?

Get started with Phishlens and run your first phishing simulation today.