CVE-2026-28400: docker model-runner Exposed Dangerous Method or Function

Vulnerability summary

CVE-2026-28400 is a high (CVSS 7.6) Exposed Dangerous Method or Function vulnerability in docker model-runner. EPSS estimates a 0.17% chance of exploitation in the next 30 days, higher than 6.2% of scored vulnerabilities.

Timeline

1. 27-02-2026
   PublishedVulnerability first disclosed.
2. 03-03-2026
   Last modifiedVulnerability information updated.

Description

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.

• CWE-749Exposed Dangerous Method or FunctionThe 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.