GHSA-X2F5-332J-9XWQ Docker Model Runner OCI Registry Client Vulnerable to Server-Side Request Forgery (SSRF)

Summary Docker Model Runner contains an SSRF vulnerability in its OCI registry token exchange flow. When pulling a model, Model Runner follows the realm URL from the registry's WWW-Authenticate header without validating the scheme, hostname, or IP range. A malicious OCI registry can set the realm...

PT-2026-29104

Name of the Vulnerable Software and Affected Versions Docker Model Runner versions prior to 1.1.25 Docker Desktop versions prior to 4.67.0 Description The software contains a Server-Side Request Forgery SSRF issue within the OCI registry token exchange process. When retrieving a model, the softwa...

Docker Desktop Docker Model Runner DoS

The vulnerability of the plugin for Docker Desktop Docker Model Runner is related to the use of dangerous methods or functions. Exploiting this vulnerability may allow a attacker to cause service failures...

Docker Desktop for Mac Docker Model Runner Exposed Dangerous Function Denial-of-Service Vulnerability

This vulnerability allows local attackers to create a denial-of-service condition on affected installations of Docker Desktop. An attacker must first obtain the ability to execute low-privileged code on the target guest system in order to exploit this vulnerability. The specific flaw exists withi...

CVE-2026-28400

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...

CVE-2026-28400

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...

CVE-2026-28400 Docker Model Runner Unauthenticated Runtime Flag Injection via _configure Endpoint

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...

CVE-2026-28400

Affected software/versions: Docker Model Runner (DMR) prior to 1.0.16. Vulnerability: POST /engines/_configure accepts arbitrary runtime flags without authentication, forwarded to the inference server (llama.cpp). Impact: via injecting --log-file, an attacker with network access can write/overwri...

EUVD-2026-9073

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...

CVE-2026-28400

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...

CVE-2026-28400 Docker Model Runner Unauthenticated Runtime Flag Injection via _configure Endpoint

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...

CVE-2026-28400 Docker Model Runner Unauthenticated Runtime Flag Injection via _configure Endpoint

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...

CVE-2026-28400: Exposed Dangerous Method or Function

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...

Docker Model Runner 安全漏洞

Docker Model Runner is an open-source Docker model runner developed by Docker. Versions of Docker Model Runner prior to 1.0.16 contained security vulnerabilities. These vulnerabilities stemmed from unvalidated POST endpoints that allowed arbitrary runtime flags to be accepted. This could enable...

PT-2026-22403

Name of the Vulnerable Software and Affected Versions Docker Model Runner versions prior to 1.0.16 Docker Desktop versions prior to 4.61.0 when Model Runner is enabled Description Docker Model Runner is software used to manage, run, and deploy AI models using Docker. Versions prior to 1.0.16 expo...

This Week in Spring - April 15th, 2025

Spring AI M7 is here! This new release includes a bunch of awesome new features! And some refactorings. Notably that the Spring AI auto-configuration has changed from a single monolithic artifact to individual auto-configuration artifacts per model, vector store, and other components. This change...