Skip to content
logo The magazine for digital lifestyle and entertainment
Artificial intelligence News Security All topics
Following OpenAI and Anthropic

Chinese AI Also Bypasses Security Tests

Logo of the Chinese AI app Kimi on a smartphone, with the Chinese flag in the background
The Chinese AI Kimi K3 acted independently, doing what was not intended. Photo: Getty Images
Share article

August 10, 2026, 9:59 am | Read time: 3 minutes

Recently, several AI models have drawn attention during security tests for bypassing intended limits or finding unexpected ways to achieve their goals. Researchers are now reporting another case. According to them, the Chinese AI model Kimi K3 exploited a vulnerability in the test environment during an evaluation by the British AI Safety Institute. This allowed it to access information not intended for the actual task.

Access to Test Files via GitHub

Security researchers Paul Kassianik and Yaron Singer from Frontier Security describe the incident in a report. Kimi K3 was tested in an isolated environment. These so-called sandboxes are designed to prevent AI models from accessing external data or services. The systems are evaluated under controlled conditions.

According to the researchers, Kimi K3 first examined its technical environment instead of directly tackling the actual task. In doing so, the model identified restrictions on accessing websites.

While most websites were blocked, GitHub remained accessible. The platform is used for managing and providing software projects and program code.

More on the topic

AI Found the Embedded Solution

According to Frontier Security, Kimi K3 used the existing connection to GitHub to download the official files of the test being used. These files also contained information on the solution to the test task. The model was able to read this data and no longer needed to complete the task in the intended manner.

However, the researchers emphasize that Kimi K3 did not fully escape the test environment. There was no unrestricted access to the internet. Frontier Security later clarified that access to websites remained largely blocked. GitHub was only accessible as an exception for maintenance purposes.

Why the Incident Is Relevant

The case, according to the researchers, highlights a problem in evaluating powerful AI systems. A correct result does not necessarily mean that a model truly possesses the tested capability.

Also of interest: AI Model Disguised as Human and Attacked

The researchers use the term “Specification Gaming” for this behavior. It means that a system finds an unexpected or unintended way to achieve a goal. Frontier Security therefore calls for stricter safeguards for similar tests. Network access should be consistently blocked and only selectively allowed.

Additionally, the researchers recommend not only evaluating the results. Commands executed, network activities, and downloaded files should also be monitored. The incident with Kimi K3 illustrates that even a small open access point can be enough to compromise the validity of a security test.

This article is a machine translation of the original German version of TECHBOOK and has been reviewed for accuracy and quality by a native speaker. For feedback, please contact us at info@techbook.de.

You have successfully withdrawn your consent to the processing of personal data through tracking and advertising when using this website. You can now consent to data processing again or object to legitimate interests.