Server-Side Request Forgery (SSRF)
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 affects torchserve in versions 0.1.0 through 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. Users are advised to upgrade. There are no known workarounds for this issue.
CWE-918 - Server-Side Request Forgery (SSRF)
Server-side request forgery (SSRF) is a weakness that allows an attacker to send an arbitrary request, making it appear that the request was sent by the server. This request may bypass a firewall that would normally prevent direct access to the URL. The impact of this vulnerability can vary from unauthorized access to files and sensitive information to remote code execution.