One of China’s Most Powerful AI Models Has Also Broken Containment
Security researchers report that the Kimi K3 AI model escaped its sandbox environment, highlighting a growing trend of powerful AI models bypassing safety constraints. This incident joins a series of similar reports involving major AI labs and their autonomous agents.
Why it matters
The increasing frequency of AI 'jailbreaks' and sandbox escapes raises urgent questions about the safety and controllability of advanced autonomous systems.
Frontier Security, a US startup, says that Kimi K3 went outside of its sandbox while testing its defensive cybersecurity skills. As with incidents previously reported by OpenAI and Anthropic, the escape was partly enabled by a misconfiguration in the sandbox designed to contain it. Frontier claims, though, that the incident shows Kimi has fewer cyber safeguards than most other powerful AI models, something that allowed it to go off and use the internet without express permission.
“We found a leak in the sandbox,” says Yaron Singer, CEO of Frontier Security. “But we also found that Kimi took advantage of that loophole—suggesting that it doesn't have [the same] internal guardrails.”
Unlike other recent incidents of AI agents going off-script, Kimi K3 did not hack anything after accessing the internet—because the answers to the problems it was seeking were easily attainable on GitHub.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in