PyPI package
torchserve
pkg:pypi/torchserve
Vulnerabilities (5)
| CVE | Sev | CVSS | KEV | Affected versions | Fixed in | Published | Description |
|---|---|---|---|---|---|---|---|
| CVE-2024-6577 | Med | 6.3 | <= 0.11.0 | — | Mar 20, 2025 | In the latest version of pytorch/serve, the script 'upload_results_to_s3.sh' references the S3 bucket 'benchmarkai-metrics-prod' without ensuring its ownership or confirming its accessibility. This could lead to potential security vulnerabilities or unauthorized access to the buc | |
| CVE-2024-35199 | Hig | 8.2 | >= 0.3.0, < 0.11.0 | 0.11.0 | Jul 19, 2024 | TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production. In affected versions the two gRPC ports 7070 and 7071, are not bound to [localhost](http://localhost/) by default, so when TorchServe is launched, these two interfaces are bound to | |
| CVE-2024-35198 | Cri | 9.8 | < 0.11.0 | 0.11.0 | Jul 19, 2024 | 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 mode | |
| CVE-2023-48299 | Med | 5.3 | >= 0.1.0, < 0.9.0 | 0.9.0 | Nov 21, 2023 | TorchServe is a tool for serving and scaling PyTorch models in production. Starting in version 0.1.0 and prior to version 0.9.0, using the model/workflow management API, there is a chance of uploading potentially harmful archives that contain files that are extracted to any locat | |
| CVE-2023-43654 | Cri | 10.0 | >= 0.1.0, < 0.8.2 | 0.8.2 | Sep 28, 2023 | 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 comprom |
- affected <= 0.11.0
In the latest version of pytorch/serve, the script 'upload_results_to_s3.sh' references the S3 bucket 'benchmarkai-metrics-prod' without ensuring its ownership or confirming its accessibility. This could lead to potential security vulnerabilities or unauthorized access to the buc
- affected >= 0.3.0, < 0.11.0fixed 0.11.0
TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production. In affected versions the two gRPC ports 7070 and 7071, are not bound to [localhost](http://localhost/) by default, so when TorchServe is launched, these two interfaces are bound to
- affected < 0.11.0fixed 0.11.0
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 mode
- affected >= 0.1.0, < 0.9.0fixed 0.9.0
TorchServe is a tool for serving and scaling PyTorch models in production. Starting in version 0.1.0 and prior to version 0.9.0, using the model/workflow management API, there is a chance of uploading potentially harmful archives that contain files that are extracted to any locat
- affected >= 0.1.0, < 0.8.2fixed 0.8.2
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 comprom