CVE-2024-35198

TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production. TorchServe 's check on allowed_urls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowed_urls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected. This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading see PR #3082. TorchServe release 0.11.0 includes the fix to address this vulnerability. Users are advised to upgrade. There are no known workarounds for this vulnerability.

TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production. TorchServe 's check on allowed_urls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowed_urls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected. This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading see PR #3082. TorchServe release 0.11.0 includes the fix to address this vulnerability. Users are advised to upgrade. There are no known workarounds for this vulnerability.

### Impact TorchServe's check on allowed_urls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowed_urls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected. ### Patches This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading: [#3082](https://github.com/pytorch/serve/pull/3082). TorchServe release 0.11.0 includes the fix to address this vulnerability. ### References * [#3082](https://github.com/pytorch/serve/pull/3082) * [TorchServe release v0.11.0](https://github.com/pytorch/serve/releases/tag/v0.11.0) Thank Kroll Cyber Risk for for responsibly disclosing this issue. If you have any questions or comments about this advisory, we ask that you contact AWS Security via our [vulnerability reporting page](https://aws.amazon.com/security/vulnerability-reporting) or directly via email to [aws-security@amazon.com](mailto:aws-security@amazon.com). Please do not create a public GitHub issue.

### Impact TorchServe's check on allowed_urls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowed_urls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected. ### Patches This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading: [#3082](https://github.com/pytorch/serve/pull/3082). TorchServe release 0.11.0 includes the fix to address this vulnerability. ### References * [#3082](https://github.com/pytorch/serve/pull/3082) * [TorchServe release v0.11.0](https://github.com/pytorch/serve/releases/tag/v0.11.0) Thank Kroll Cyber Risk for for responsibly disclosing this issue. If you have any questions or comments about this advisory, we ask that you contact AWS Security via our [vulnerability reporting page](https://aws.amazon.com/security/vulnerability-reporting) or directly via email to [aws-security@amazon.com](mailto:aws-security@amazon.com). Please do not create a public GitHub issue.

TorchServe es una herramienta flexible y fácil de usar para servir y escalar modelos PyTorch en producción. La verificación de TorchServe en la configuración de Allow_urls se puede omitir si la URL contiene caracteres como ".." pero no impide que el modelo se descargue en la tienda de modelos. Una vez que se descarga un archivo, se puede hacer referencia a él sin proporcionar una URL la segunda vez, lo que efectivamente evita la verificación de seguridad de Allow_urls. Los clientes que utilizan contenedores de aprendizaje profundo (DLC) de inferencia de PyTorch a través de Amazon SageMaker y EKS no se ven afectados. Este problema en TorchServe se solucionó validando la URL sin caracteres como ".." antes de descargar, consulte PR #3082. La versión 0.11.0 de TorchServe incluye la solución para solucionar esta vulnerabilidad. Se recomienda a los usuarios que actualicen. No se conocen workarounds para esta vulnerabilidad.