https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Fri, 02 Oct 2026 18:39:47 +0000 https://cve.radiocsirt.org/vuln/bdu:2026-10963 bdu:2026-10963 https://cve.radiocsirt.org/vuln/bdu:2026-10963 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-2026-321584 EUVD-2026-321584 https://cve.radiocsirt.org/vuln/euvd-2026-321584 https://cve.radiocsirt.org/vuln/fkie_cve-2026-5817 <p>The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered.</p> <p>Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.</p> <p>The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered.</p> <p>Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.</p> https://cve.radiocsirt.org/vuln/fkie_cve-2026-5817 https://cve.radiocsirt.org/vuln/ghsa-cgqp-ww2v-6rjh <p>The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered.</p> <p>Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.</p> <p>The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered.</p> <p>Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.</p> https://cve.radiocsirt.org/vuln/ghsa-cgqp-ww2v-6rjh 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