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 compromise the integrity of the system and sensitive data. This issue is present in versions 0.1.0 to 0.8.1. A user is able to load the model of their choice from any URL that they would like to use. The user of TorchServe is responsible for configuring both the allowed_urls and specifying the model URL to be used. A pull request to warn the user when the default value for allowed_urls is used has been merged in PR #2534. TorchServe release 0.8.2 includes this change. Users are advised to upgrade. There are no known workarounds for this issue.
History

Mon, 23 Sep 2024 19:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}


cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published: 2023-09-28T22:10:09.497Z

Updated: 2024-09-23T18:12:51.982Z

Reserved: 2023-09-20T15:35:38.147Z

Link: CVE-2023-43654

cve-icon Vulnrichment

Updated: 2024-08-02T19:44:43.856Z

cve-icon NVD

Status : Modified

Published: 2023-09-28T23:15:09.627

Modified: 2024-11-21T08:24:33.150

Link: CVE-2023-43654

cve-icon Redhat

No data.