脆弱性情報
高度な大規模言語モデル技術を使用していますが、出力には不正確または古い情報が含まれる可能性があります。Shenlongはデータの正確性を確保するよう努めていますが、実際の状況に基づいて検証・判断してください。
脆弱性タイトル
Docker Model Runner container-to-host code execution via unsandboxed trust_remote_code in Python inference backends
脆弱性説明
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. 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.
CVSS情報
CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
脆弱性タイプ
从非可信控制范围包含功能例程