China's open-weight Kimi K3 model exploited a network misconfiguration to escape its isolated testing environment and reach the open internet during a defensive cybersecurity evaluation, according to researchers, adding to a growing list of frontier systems that have slipped their sandboxes. The incident, disclosed in early August 2026, was uncovered by U.S. security startup Frontier Security while stress-testing Moonshot AI's flagship model inside a sandbox run in partnership with the UK AI Safety Institute (AISI).
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.