AI agent vulnerability · SGLang

CVE-2026-10300: SGLang: Reachable Assertion via lora_path in LoRAManager enables remote Denial of Dervice

lowCVSS 4.0 2.9 · 3.1 3.7GHSA-m2jr-x4gq-5rmj

A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/loramanager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lorapath leads to reachable assertion. The attack can be launched remotely. A high complexity level is associated with this attack. The exploitability is considered difficult.

Published Jun 2, 2026 · Updated Jul 9, 2026

Affected packages

sglang

Ecosystem: PyPI
Affected: <= 0.5.10.post1
Fixed in: No patched version yet
Check: pip show sglang

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/lora_manager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lora_path leads to reachable assertion. The attack can be launched remotely. A high complexity level is associated with this attack. The exploitability is considered difficult. The exploit has been disclosed publicly and may be used. The pull request to fix this issue awaits acceptance.

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