OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot

Summary

Hacktron AI, a US-based startup, used Anthropic's Claude chatbot, and mainly OpenAI's GPT-5.6 Sol model, to compromise several OpenAI employees' ChatGPT accounts through an internal staff discussion forum hosted on Discourse. The researchers then made a harmless pull request to OpenAI's service on GitHub, reaching access to the software cache, though they say they viewed but did not download the code. Hacktron reported the work under an OpenAI bug bounty program and received $6,500.

Related items

• InfoSilicon Valley claims to know the future. So why did it get the midterms so wrong?Same vendor · MIT Technology Review
• InfoOpenAI Unveils Daybreak Red Team, Defense Factory Security ToolsSame vendor · SecurityWeek
• InfoAn AI kill switch isn’t enough. Build a fallback planSame vendor · CSO Online
• InfoJim Cramer has three lingering questions about Anthropic ahead of its historic IPOSame vendor · CNBC Technology
• MediumGHSA-68g8-gh8f-7rhg: pgEdge RAG Server discloses part of the configured provider credential through API error messagesSame vendor · GitHub Advisory Database