AI agent vulnerability · TorchServe

CVE-2024-35198: TorchServe vulnerable to bypass of allowed_urls configuration

criticalCVSS 4.0 9.3 · 3.1 9.8GHSA-wxcx-gg9c-fwp2

Impact TorchServe's check on allowedurls 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 allowedurls security check.

Published Jul 18, 2024 · Updated Aug 7, 2024

Affected packages

torchserve

Ecosystem: PyPI
Affected: < 0.11.0
Fixed in: 0.11.0
Check: pip show torchserve

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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.

TorchServe release 0.11.0 includes the fix to address this vulnerability.

References

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 or directly via email to [[email protected]](mailto:[email protected]). Please do not create a public GitHub issue.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More TorchServe vulnerabilities

All TorchServe entries