CVE-2026-127222

7.5High

Published 18 Nov 2026 · NVD status: Deferred · AI triage by gemini-3.1-flash-lite

7.5CVSS

High

0CVSS v3.110

Attack vector
Network
Complexity
Low
Privileges
None
User action
None
Impact
High impact on integrity
Weakness
CWE-862

What an attacker gets

Unauthenticated network attackers can load arbitrary LoRA adapters to manipulate model output. This can be chained with a deserialization bypass to achieve remote code execution as root.

Root cause

The /load_lora_adapter_from_tensors endpoint is missing the required admin authorization decorator.

Affected versions

SGLang through 0.5.23

CVSS v3.1 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N

Fix & remediation

Upgrade to a version containing commit 7b5fb39. Until patched, block network access to the SGLang API endpoint /load_lora_adapter_from_tensors at the firewall or reverse proxy level.

remediation — bash
$ pip install --upgrade sglang

AI-suggested. Run it in staging first and check it against the vendor advisory. Why?

NVD description

SGLang through 0.5.23, fixed in commit 7b5fb39, contains a missing authorization vulnerability in the POST /load_lora_adapter_from_tensors HTTP endpoint, which lacks the @auth_level(AuthLevel.ADMIN_OPTIONAL) decorator applied to its sibling admin endpoints, allowing unauthenticated network-reachable attackers to invoke it without an API key. Attackers can load a LoRA adapter from attacker-supplied serialized tensors to manipulate the served model, and when combined with a separately documented deserialization bypass, achieve unauthenticated remote code execution as root.

References

Source: nvd.nist.gov/vuln/detail/CVE-2026-127222