You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
namannandan
published
GHSA-8fxr-qfr9-p34wSep 28, 2023
Package
torchserve
Affected versions
0.1.0 >= 0.8.1
Patched versions
0.8.2
Description
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 allowed_urls and specifying the model URL to be used. A pull request to warn the user when the default value for allowed_urls is used has been merged - #2534. TorchServe release 0.8.2 includes this change.
Patches
TorchServe release 0.8.2 includes fixes to address the previously listed issue:
*`allowed_urls` : Comma separated regex of allowed source URL(s) from where models can be registered. Default: `file://.*|http(s)?://.*` (all URLs and local file system)
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 [email protected]. Please do not create a public GitHub issue.
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
0.1.0to0.8.1.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 allowed_urls and specifying the model URL to be used. A pull request to warn the user when the default value for
allowed_urlsis used has been merged - #2534. TorchServe release0.8.2includes 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
x86 CPU
Graviton
Neuron
The full DLC image URI details can be found at: https://github.com/aws/deep-learning-containers/blob/master/available_images.md#available-deep-learning-containers-images
References
serve/docs/configuration.md
Line 296 in b3eced5
#2534
https://github.com/pytorch/serve/releases/tag/v0.8.2
https://github.com/aws/deep-learning-containers/blob/master/available_images.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 [email protected]. Please do not create a public GitHub issue.