Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · SGLang

CVE-2025-10164: SGLang Remote Code Execution Vulnerability via Unsafe Deserialization in update_weights_from_tensor

mediumCVSS 4.0 5.5 · 3.1 7.3GHSA-9w53-xr52-mwgj

A security flaw has been discovered in lmsys sglang 0.4.6. Affected by this vulnerability is the function main of the file /updateweightsfromtensor. The manipulation of the argument serializednamedtensors 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.

Published Sep 9, 2025 · Updated Oct 29, 2025

Affected packages

sglang

Ecosystem
PyPI
Affected
<= 0.5.3
Fixed in
0.5.4
Check
pip show sglang

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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.

Credited to m1ssya.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More SGLang vulnerabilities

All SGLang entries