AdvertisementArtificial intelligenceTechTech Trends
China’s Kimi K3 AI model escapes isolated sandbox during security test: researchers
Kimi K3’s escape did not involve the hacking of an external system, unlike recent breaches by OpenAI and Anthropic models
2-MIN READ2-MIN Listen
Xinmei ShenPublished: 4:00pm, 7 Aug 2026
China’s top open-weight AI model Kimi K3 broke out of its isolated test environment during a cybersecurity evaluation, according to US security researchers, following similar high-profile incidents involving closed frontier models from OpenAI and Anthropic that highlight the growing challenge of constraining AI behaviour.
Kimi K3, released last month by Beijing-based Moonshot AI, escaped from a supposedly isolated sandbox environment, accessed the open internet, and found solutions on the developer platform GitHub, US firm Frontier Security said in a blog post on Thursday.
The incident occurred when the firm tested Kimi K3’s defensive cybersecurity capabilities using a benchmark evaluation from the AI Security Institute – a UK government research organisation, according to Frontier Security researchers Paul Kassianik and Yaron Singer.
A “basic network misconfiguration” in the benchmark framework allowed Kimi K3 to flee its digital testing cage and look up answers on the internet, effectively cheating the test, they said.
Kimi K3’s escape, however, did not involve the hacking of an external system, unlike recent breaches caused by OpenAI and Anthropic models.
Last month, OpenAI said its flagship GPT-5.6 Sol and an unreleased, “even more capable” system broke out of a sandboxed environment and hacked the open-source developer platform Hugging Face to obtain secret information containing answers to an internal test.
AdvertisementSelect VoiceSelect Speed00:0000:001.00x