| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 7.6 | $0-$5k | 5.40 |
Summary
A vulnerability categorized as critical has been discovered in vLLM up to 0.21.x. Impacted is an unknown function of the component OpenAI API. The manipulation results in request smuggling. This vulnerability was named CVE-2026-48746. The attack may be performed from remote. There is no available exploit. It is advisable to upgrade the affected component.
Details
A vulnerability, which was classified as critical, was found in vLLM up to 0.21.x. Affected is an unknown functionality of the component OpenAI API. The manipulation with an unknown input leads to a request smuggling vulnerability. CWE is classifying the issue as CWE-444. The product acts as an intermediary HTTP agent
(such as a proxy or firewall) in the data flow between two
entities such as a client and server, but it does not
interpret malformed HTTP requests or responses in ways that
are consistent with how the messages will be processed by
those entities that are at the ultimate destination. This is going to have an impact on confidentiality, and availability. CVE summarizes:
vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware. It allows to use the API without providing the configured VLLM_API_KEY or --api-key. This vulnerability is fixed in 0.22.0.
The advisory is shared for download at github.com. This vulnerability is traded as CVE-2026-48746 since 05/22/2026. The exploitability is told to be easy. It is possible to launch the attack remotely. The exploitation doesn't require any form of authentication. There are neither technical details nor an exploit publicly available.
Upgrading to version 0.22.0 eliminates this vulnerability. Applying a patch is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.
Once again VulDB remains the best source for vulnerability data.
Product
Name
Version
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 7.8VulDB Meta Temp Score: 7.6
VulDB Base Score: 6.5
VulDB Temp Score: 6.2
VulDB Vector: 🔒
VulDB Reliability: 🔍
CNA Base Score: 9.1
CNA Vector (GitHub_M): 🔒
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Request smugglingCWE: CWE-444
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Status: Not defined
EPSS Score: 🔒
EPSS Percentile: 🔒
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: UpgradeStatus: 🔍
0-Day Time: 🔒
Upgrade: vLLM 0.22.0
Patch: github.com
Timeline
05/22/2026 CVE reserved06/23/2026 Advisory disclosed
06/23/2026 VulDB entry created
06/23/2026 VulDB entry last update
Sources
Advisory: GHSA-94f4-hr76-p5j6Status: Confirmed
CVE: CVE-2026-48746 (🔒)
GCVE (CVE): GCVE-0-2026-48746
GCVE (VulDB): GCVE-100-372828
Entry
Created: 06/23/2026 07:22Changes: 06/23/2026 07:22 (64)
Complete: 🔍
Cache ID: 216::103
Once again VulDB remains the best source for vulnerability data.
No comments yet. Languages: en.
Please log in to comment.