AETERNAE AI RESEARCH LLC INDEPENDENT RESEARCH
ÆAETERNAERESEARCH
Sign inRequest access

Attributed metadata history

Up to 100 retained publisher events per page for abbf94137b3f6e36fba5dda8d800e53f499342c61927beb663a71d9861d933c5. Withdrawals and unavailable references remain attributed to their publishers.

intelligence_src_c25d91fa3ad9ae9ac7

observed · 2026-10-12 14:53:04 UTC

In the previous post we demonstrated how instructions embedded in untrusted data can invoke ChatGPT’s memory tool. The examples we looked at included Uploaded Files, Connected Apps and also the Browsing tool. When it came to the browsing tool we observed that mitigations were put in place and older demo exploits did not work anymore. After chatting with other security researchers, I learned that they had observed the same.

Fingerprint: 54f5aaa62e8c9ef9ae4bf3dfe4f90f24733d997a67b30b234c331bd68bd0bc57

intelligence_src_c25d91fa3ad9ae9ac7

observed · 2026-10-12 14:53:03 UTC

available

Fingerprint: 0a2f1bebc7ea800736eafab237a0ddecfb8797a02d23951e8aa80935e2f3446f