CVE-2023-43654: TorchServe Server-Side Request Forgery
Impact Remote Server-Side Request Forgery (SSRF) Issue: TorchServe default configuration lacks proper input validation, enabling third parties to invoke remote HTTP download requests and write files to the disk. This issue could be taken advantage of to compromise the integrity of the system and sensitive data. This issue is present in versions 0.1.0 to 0.8.1. Mitigation: The user is able to load the model of their choice from any URL that they would like to use. The user of TorchServe is responsible for configuring both the allowedurls and specifying the model URL to be used. A pull request to warn the user when the default value for allowedurls is used has been merged - https://github.com/pytorch/serve/pull/2534. TorchServe release 0.8.2 includes this change.
Patches
TorchServe release 0.8.2 includes fixes to address the previously listed issue:
https://github.com/pytorch/serve/releases/tag/v0.8.2
Tags for upgraded DLC release User can use the following new image tags to pull DLCs that ship with patched TorchServe version 0.8.2: x86 GPU
v1.9-pt-ec2-2.0.1-inf-gpu-py310 v1.8-pt-sagemaker-2.0.1-inf-gpu-py310
x86 CPU
v1.8-pt-ec2-2.0.1-inf-cpu-py310 v1.7-pt-sagemaker-2.0.1-inf-cpu-py310
Graviton
v1.7-pt-graviton-ec2-2.0.1-inf-cpu-py310 v1.5-pt-graviton-sagemaker-2.0.1-inf-cpu-py310
Neuron
1.13.1-neuron-py310-sdk2.13.2-ubuntu20.04 1.13.1-neuronx-py310-sdk2.13.2-ubuntu20.04 1.13.1-neuronx-py310-sdk2.13.2-ubuntu20.04
The full DLC image URI details can be found at: https://github.com/aws/deep-learning-containers/blob/master/availableimages.md#available-deep-learning-containers-images
References https://github.com/pytorch/serve/blob/b3eced56b4d9d5d3b8597aa506a0bcf954d291bc/docs/configuration.md?plain=1#L296 https://github.com/pytorch/serve/pull/2534 https://github.com/pytorch/serve/releases/tag/v0.8.2 https://github.com/aws/deep-learning-containers/blob/master/availableimages.md#available-deep-learning-containers-images
Credit We would like to thank Oligo Security for responsibly disclosing this issue and working with us on its resolution. If you have any questions or comments about this advisory, we ask that you contact AWS/Amazon Security via our vulnerability reporting page](https://aws.amazon.com/security/vulnerability-reporting)) or directly via email to aws-security@amazon.com. Please do not create a public GitHub issue.
Other sources
TorchServe is a tool for serving and scaling PyTorch models in production. TorchServe default configuration lacks proper input validation, enabling third parties to invoke remote HTTP download requests and write files to the disk. This issue could be taken advantage of to compromise the integrity of the system and sensitive data. This issue is present in versions 0.1.0 to 0.8.1. A user is able to load the model of their choice from any URL that they would like to use. The user of TorchServe is responsible for configuring both the allowedurls and specifying the model URL to be used. A pull request to warn the user when the default value for allowedurls is used has been merged in PR #2534. TorchServe release 0.8.2 includes this change. Users are advised to upgrade. There are no known workarounds for this issue.
Affected Software
Event History
Frequently Asked Questions
What is CVE-2023-43654?
CVE-2023-43654 is a vulnerability in TorchServe, a tool for serving and scaling PyTorch models in production.
What is the impact of CVE-2023-43654?
The impact of CVE-2023-43654 is Remote Server-Side Request Forgery (SSRF). It allows third parties to invoke remote HTTP download requests and write files to the disk, compromising the integrity of the system.
How severe is CVE-2023-43654?
CVE-2023-43654 has a severity rating of 9.8 (critical).
How can I fix CVE-2023-43654?
To fix CVE-2023-43654, update TorchServe to version 0.8.2 or later.
Where can I find more information about CVE-2023-43654?
You can find more information about CVE-2023-43654 on the GitHub page for TorchServe, the PyTorch Serve releases page, and the PyTorch Serve security advisories page.