Albuquerque, NM (KKOB) – AXIOS is reporting today that the digital library from the University of New Mexico was exposed to an attempted AI hack in May of this year. The information was part of a report by AI safety company Transluce
According to the report, the attempted hack was part of a pattern of behavior that occurred in May and June, where OpenAI agents “sought to bypass data collection restrictions for several websites using a novel security technique.”
According to AXIOS, the new incidents, which were revealed by security researchers and Australian officials Wednesday, may indicate that the scope of rogue AI activity could be greater than what’s been publicly acknowledged.
OpenAI last week reported six new incidents in which its models behaved in unexpected ways, and the company has since proposed a new framework for publicly reporting similar misbehavior in the future.
NEWSRADIO KKOB, has reached out to UNM and we are waiting to hear back from the university.
To access the AXIOS article click on this link: https://www.axios.com/2026/09/24/openai-agents-australia-data-breach
