https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Sat, 03 Oct 2026 15:23:16 +0000 https://cve.radiocsirt.org/vuln/certfr-2026-avi-0620 certfr-2026-avi-0620 https://cve.radiocsirt.org/vuln/certfr-2026-avi-0620 https://cve.radiocsirt.org/vuln/euvd-2026-321585 EUVD-2026-321585 https://cve.radiocsirt.org/vuln/euvd-2026-321585 https://cve.radiocsirt.org/vuln/fkie_cve-2026-5843 <p>The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the model_file configuration field in config.json. When a model&#39;s config.json specifies a model_file pointing to a Python file, MLX-LM uses importlib to load and execute it with no trust_remote_code gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.</p> <p>Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model from an attacker-controlled OCI registry and request inference.</p> <p>The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the model_file configuration field in config.json. When a model&#39;s config.json specifies a model_file pointing to a Python file, MLX-LM uses importlib to load and execute it with no trust_remote_code gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.</p> <p>Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model from an attacker-controlled OCI registry and request inference.</p> https://cve.radiocsirt.org/vuln/fkie_cve-2026-5843 https://cve.radiocsirt.org/vuln/ghsa-9m9w-53g9-47c4 <p>The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the model_file configuration field in config.json. When a model&#39;s config.json specifies a model_file pointing to a Python file, MLX-LM uses importlib to load and execute it with no trust_remote_code gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.</p> <p>Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model from an attacker-controlled OCI registry and request inference.</p> <p>The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the model_file configuration field in config.json. When a model&#39;s config.json specifies a model_file pointing to a Python file, MLX-LM uses importlib to load and execute it with no trust_remote_code gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.</p> <p>Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model from an attacker-controlled OCI registry and request inference.</p> https://cve.radiocsirt.org/vuln/ghsa-9m9w-53g9-47c4 https://cve.radiocsirt.org/vuln/wid-sec-w-2026-1662 <p>Ein Angreifer kann mehrere Schwachstellen in Docker Desktop Model Runner ausnutzen, um beliebigen Programmcode auszuführen.</p> <p>Ein Angreifer kann mehrere Schwachstellen in Docker Desktop Model Runner ausnutzen, um beliebigen Programmcode auszuführen.</p> https://cve.radiocsirt.org/vuln/wid-sec-w-2026-1662