AI Security Researchers Claim to Hack ChatGPT Using Claude

Security experts hack ChatGPT using Claude, raising alarms about AI vulnerabilities. OpenAI addresses breach and pays bounty.

Editorial Desk

September 18, 2026 One Min Read

POLICY WIRE — City, Country — A group of AI security researchers has claimed to exploit OpenAI’s ChatGPT using Anthropic’s Claude platform, highlighting growing concerns over the security of major AI systems.

Hacktron AI, an independent AI security firm, revealed the breach in a blog post, stating they accessed an OpenAI employee’s ChatGPT account through Claude. This allowed them to uncover critical information about where the source code was stored and managed, as well as access an internal discussion forum.

📄 POLICY WIRE WHITEPAPER PUBLISHED: PAKISTAN’S NATIONAL SECURITY POLICY PRIORITIES

👉 READ BY CLICKING HERE

The researchers disclosed the vulnerability to OpenAI, which issued a $6,500 reward for the report. OpenAI confirmed it had taken steps to address the issue by limiting permissions on community sign-in tokens and revoking affected sessions. The incident was first reported by The Wall Street Journal.

Reporting by Policy-Wire (PW)

Author

Editorial Desk

Policy Wire is your go-to editorial hub for insightful perspectives and informed analysis on pressing policy issues, both regionally and globally. Over the years, Policy Wire has collaborated with leading international news agencies—including AFP, AP, Reuters, and others—to provide fact-based reporting and nuanced commentary. With a commitment to clarity and credibility, we aim to bridge the gap between complex policy debates and public understanding, ensuring that our readers stay informed on the issues shaping the world today.