Docker Model Runner (DMR) is software used to manage, run, and deploy AI models using Docker. Versions prior to 1.0.16 expose a POST /engines/_configure endpoint that accepts arbitrary runtime flags without authentication. These flags are passed directly to the underlying inference server (llama.cpp). By injecting the –log-file flag, an attacker with network access to the Model Runner API can write or overwrite arbitrary files accessible to the Model Runner process. When bundled with Docker Desktop (where Model Runner is enabled by default since version 4.46.0), it is reachable from any default container at model-runner.docker.internal without authentication. In this context, the file overwrite can target the Docker Desktop VM disk (Docker.raw ), resulting in the destruction of all containers, images, volumes, and build history. However, in specific configurations and with user interaction, it is possible to convert this vulnerability in a container escape. The issue is fixed in Docker Model Runner 1.0.16. Docker Desktop users should update to 4.61.0 or later, which includes the fixed Model Runner. A workaround is available. For Docker Desktop users, enabling Enhanced Container Isolation (ECI) blocks container access to Model Runner, preventing exploitation. However, if the Docker Model Runner is exposed to localhost over TCP in specific configurations, the vulnerability is still exploitable.
Weakness
The product provides an Applications Programming Interface (API) or similar interface for interaction with external actors, but the interface includes a dangerous method or function that is not properly restricted.
Extended Description
This weakness can lead to a wide variety of resultant weaknesses, depending on the behavior of the exposed method. It can apply to any number of technologies and approaches, such as ActiveX controls, Java functions, IOCTLs, and so on. The exposure can occur in a few different ways:
Potential Mitigations
Identify all exposed functionality. Explicitly list all functionality that must be exposed to some user or set of users. Identify which functionality may be:
Ensure that the implemented code follows these expectations. This includes setting the appropriate access modifiers where applicable (public, private, protected, etc.) or not marking ActiveX controls safe-for-scripting.