business
OpenAI hacked by small team of white hat security researchers using Anthropic's Claude Opus 5
For enterprise teams, the larger lesson extends beyond one vulnerable image decoder. AI agents are increasingly being given credentials and connectors that span source code, communications and corporate data.
Security researchers say they used Anthropic’s newly released Claude Opus 5 to help turn an image-processing vulnerability into an exploit chain that compromised an OpenAI employee’s ChatGPT account and reached the company’s internal GitHub environme... [7065 chars]
Read Full ArticleShare this story
Up next
Related Stories
Major banks raise interest rates after RBA lifts cash rate to highest since 2011
abc.net.au
Back carriages on Tangara train services shut for school holidays amid security breaches
abc.net.au
Madonna beats Taylor Swift in MTV awards showdown
abc.net.au
Rewards programs and insurance perks in firing line after changes to bank surcharging rules
abc.net.au
From vines to vegetation, property becomes safe haven for an endangered bird species
abc.net.au