GHSA-9w53-xr52-mwgj

SGLang Remote Code Execution Vulnerability via Unsafe Deserialization in update_weights_from_tensor

Source: GitHub Advisory Database (reviewed) Moderate CVE-2025-10164

Packages

Ecosystem	Package	Affected	Fixed in
PyPI	sglang	< 0.5.4	0.5.4

Details

As written in the advisory (Markdown source, shown as plain text).

A security flaw has been discovered in lmsys sglang 0.4.6. Affected by this vulnerability is the function main of the file /update_weights_from_tensor. The manipulation of the argument serialized_named_tensors results in deserialization. The attack can be launched remotely. The exploit has been released to the public and may be exploited. The vendor was contacted early about this disclosure but did not respond in any way.

References

External links from the advisory. They lead to third-party sites.

https://nvd.nist.gov/vuln/detail/CVE-2025-10164 advisory
https://github.com/sgl-project/sglang/commit/49afb3d9d9deedf6dea3a6dd5c50e85e7d8bcb07 web
https://github.com/sgl-project/sglang package
https://vuldb.com/?ctiid.323203 web
https://vuldb.com/?id.323203 web
https://vuldb.com/?submit.635919 web