Vulnerability · Published Jun 1, 2026 · Assigned by VulDB
CVE-2026-10300SGLang Inference HTTP Endpoint lora_manager.py assertion
Low 3.7
In plain English
A low-severity security flaw in SGLang. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 31% of all known vulnerabilities).
Official description
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | sglang | no fix listed | GHSA-m2jr-x4gq-5rmj |
| PyPI | sglang | no fix listed | PYSEC-2026-3064 |
Affected products (as reported)
Weakness: CWE-617 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L/E:P/RL:X/RC:R
References
- VDB-367593 | SGLang Inference HTTP Endpoint lora_manager.py assertion vdb-entry, technical-description
- VDB-367593 | CTI Indicators (IOB, IOC, IOA) signature, permissions-required
- CVE-2026-10300 | CVE Analysis and Report third-party-advisory
- Submit #828086 | SGLang Project (sgl-project) SGLang 0.5.10.post1 Reachable Assertion third-party-advisory
- https://github.com/sgl-project/sglang/issues/23141 exploit, issue-tracking
- https://github.com/sgl-project/sglang/pull/25078 issue-tracking, patch