https://patchthecve.com/CVEs with upgrade or downgrade fix stepshttps://patchthecve.com/cve/CVE-2024-35199.htmlhttps://patchthecve.com/cve/CVE-2024-35199.htmlWed, 17 Jun 2026 07:34:31 +0000HIGH 8.2: 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 all interfaces. Cushttps://patchthecve.com/cve/CVE-2024-35198.htmlhttps://patchthecve.com/cve/CVE-2024-35198.htmlWed, 17 Jun 2026 07:34:31 +0000CRITICAL 9.8: 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 filehttps://patchthecve.com/cve/CVE-2023-48299.htmlhttps://patchthecve.com/cve/CVE-2023-48299.htmlWed, 17 Jun 2026 06:33:57 +0000MEDIUM 5.3: 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 location on the filesyste