Skip to main content
CVE-2026-127222VulnerabilityPublished

SGLang through 0.5.23, fixed

Source GCVE Database

0
Compare
Authoritative record:CVE-2026-127222· High 8.7

Not known to be exploited · CVSS 8.7 High.

Data as of 18 Nov 2026, 22:50 UTC

CVSS 4.0 base score
8.7High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (VulnCheck)CVSS 4.08.7
CNA (VulnCheck)CVSS 3.17.5
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 18 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 18 Nov 2026.

What to do

Affected software

ProductAffectedFixed in
sgl-projectsglangAffected
  • <=0.5.23
Fixed in–
PyPIsglangpkg:pypi/sglangOther threatsAffected
  • <=0.5.23
Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

A fix for this vulnerability is available in commit 7b5fb39. Users should update SGLang to a version that includes this commit to ensure the missing authorization check is applied. Until patched, restrict network access to the affected endpoint to trusted users only. There is no indication that this vulnerability is mitigated by default or requires no action.

Description

SGLang versions through 0.5.23 have a missing authorization vulnerability in the POST /load_lora_adapter_from_tensors endpoint. This endpoint lacks the required admin-level authorization decorator, allowing unauthenticated attackers to invoke it without an API key. Exploiting this flaw, attackers can load a LoRA adapter from attacker-supplied serialized tensors to manipulate the served model. When combined with a separate deserialization bypass vulnerability, this can lead to unauthenticated remote code execution as root. The vulnerability has a high severity score of 7.5 and was fixed in commit 7b5fb39.

References

Community reviews

Loading reviews…