CVE-2024-35198
TorchServe bypass allowed_urls configuration
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
TorchServe bypass allowed_urls configuration
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.
- Record
CVE-2024-35198- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-706
- Updated
- 2026-11-02
EUVDEUVD-2024-2442
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.
- Record
EUVD-2024-2442- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Updated
- 2026-11-03
GitHub AdvisoriesGHSA-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]. Please do not create a public GitHub issue.
- Record
GHSA-wxcx-gg9c-fwp2- CVSS 4.0
- 9.3 Critical
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-22, CWE-706
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2024-35198- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-706
- Updated
- 2026-11-02
OSV
TorchServe bypass allowed_urls configuration
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.
- Record
CVE-2024-35198- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-706
- Updated
- 2026-11-02
OSVGHSA-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]. Please do not create a public GitHub issue.
- Record
GHSA-wxcx-gg9c-fwp2- CVSS 4.0
- 9.3 Critical
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-22, CWE-706
- Updated
- 2026-11-02
OSVPYSEC-2026-554
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]. Please do not create a public GitHub issue.
- Record
PYSEC-2026-554- CVSS 4.0
- 9.3 Critical
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
torchservePyPI |
before 0.11.0 | 0.11.0 |
torchservePyPI |
before 0.11.0, plus listed versions 0.0.1b202004090.1.10.10.00.2.00.2.2 Show 17 moreShow less0.3.00.3.10.4.00.4.10.4.20.5.00.5.10.5.20.5.30.6.00.6.10.7.00.7.10.8.00.8.10.8.20.9.0 |
0.11.0 |
History
| Recorded | Changed | Sources |
|---|---|---|
| aliases | EUVD | |
| first indexed | CVE List, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2024-35198 is a critical vulnerability (CVSS 9.8) in Pytorch Serve, published July 18, 2024. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.80%, the 56th percentile. Fixed in torchserve 0.11.0.
References
github.com/pytorch/serve/security/advisories/GHSA-wxcx-gg9c-fwp2
nvd.nist.gov/vuln/detail/CVE-2024-35198
pypi.org/project/torchserve