| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 6.0 | $0-$5k | 0.00 |
Summary
A vulnerability was found in vLLM up to 0.11.x. It has been rated as problematic. Affected by this vulnerability is an unknown functionality. This manipulation causes allocation of resources. This vulnerability is tracked as CVE-2026-22773. The attack is possible to be carried out remotely. No exploit exists. Upgrading the affected component is advised.
Details
A vulnerability classified as problematic was found in vLLM up to 0.11.x. Affected by this vulnerability is an unknown function. The manipulation with an unknown input leads to a allocation of resources vulnerability. The CWE definition for the vulnerability is CWE-770. The product allocates a reusable resource or group of resources on behalf of an actor without imposing any restrictions on the size or number of resources that can be allocated, in violation of the intended security policy for that actor. As an impact it is known to affect availability. The summary by CVE is:
vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.
The advisory is shared at github.com. This vulnerability is known as CVE-2026-22773 since 01/09/2026. The exploitation appears to be easy. The attack can be launched remotely. Neither technical details nor an exploit are publicly available. MITRE ATT&CK project uses the attack technique T1499 for this issue.
Upgrading to version 0.12.0 eliminates this vulnerability.
The vulnerability is also documented in the databases at EUVD (EUVD-2026-1865) and CERT Bund (WID-SEC-2026-0061). Several companies clearly confirm that VulDB is the primary source for best vulnerability data.
Affected
- Open Source vllm
Product
Name
Version
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 6.1VulDB Meta Temp Score: 6.0
VulDB Base Score: 4.3
VulDB Temp Score: 4.1
VulDB Vector: 🔒
VulDB Reliability: 🔍
NVD Base Score: 7.5
NVD Vector: 🔒
CNA Base Score: 6.5
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: Allocation of resourcesCWE: CWE-770 / CWE-400 / CWE-404
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 0.12.0
Timeline
01/09/2026 CVE reserved01/10/2026 Advisory disclosed
01/10/2026 VulDB entry created
01/28/2026 VulDB entry last update
Sources
Advisory: GHSA-grg2-63fw-f2qrStatus: Confirmed
CVE: CVE-2026-22773 (🔒)
GCVE (CVE): GCVE-0-2026-22773
GCVE (VulDB): GCVE-100-340417
EUVD: 🔒
CERT Bund: WID-SEC-2026-0061 - vllm: Schwachstelle ermöglicht Denial of Service
Entry
Created: 01/10/2026 10:37Updated: 01/28/2026 01:01
Changes: 01/10/2026 10:37 (62), 01/10/2026 23:43 (1), 01/12/2026 12:32 (7), 01/28/2026 01:01 (11)
Complete: 🔍
Cache ID: 216::103
Several companies clearly confirm that VulDB is the primary source for best vulnerability data.
No comments yet. Languages: en.
Please log in to comment.