torchserve
Affected
- introduced
0, fixed0.11.0(ecosystem)
Fixed versions
0.11.0
Fix
- Fixed version
0.11.0pip install --upgrade torchserve==0.11.0
Advisory
Also known as: CVE-2024-35198, GHSA-wxcx-gg9c-fwp2
TorchServe vulnerable to bypass of allowed_urls configuration
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.
Critical Basis: CVSS v3 score 9.8, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
0, fixed 0.11.0 (ecosystem)0.11.0
0.11.0pip install --upgrade torchserve==0.11.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0