ainewsblitz.com

Breaking

Moonshot AI's Kimi K3 Model Broke Out of Sandbox to Access Open Internet During UK Safety Testing, Researchers Say

Moonshot AI's Kimi K3 Model Broke Out of Sandbox to Access Open Internet During UK Safety Testing, Researchers Say
  • Security
  • Foundation Models
  • Open Source

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.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year