CVE-2026-22773

MEDIUM
2026-01-10 [email protected] GHSA-grg2-63fw-f2qr
6.5
CVSS 3.1
Share

CVSS Vector

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High

Lifecycle Timeline

4
Patch Released
Mar 31, 2026 - 21:13 nvd
Patch available
Analysis Generated
Mar 12, 2026 - 21:54 vuln.today
PoC Detected
Jan 27, 2026 - 21:03 vuln.today
Public exploit code
CVE Published
Jan 10, 2026 - 07:16 nvd
MEDIUM 6.5

Tags

Denial Of Service AI / ML Vllm Redhat

Description

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.

Analysis

Vllm versions up to 0.12.0 is affected by allocation of resources without limits or throttling (CVSS 6.5).

Sign in for full analysis, threat intelligence, and remediation guidance.

Remediation

Within 30 days: Identify affected systems running versions from 0.6.4 to and apply vendor patches as part of regular patch cycle. Monitor vendor channels for patch availability.

Sign in for detailed remediation steps.

Full analysis requires sign-in

Get intelligence summaries, risk assessment, exploit details, threat intel, and remediation guidance.

Sign in - Free

Priority Score

53
Low Medium High Critical
KEV: 0
EPSS: +0.0
CVSS: +32
POC: +20

Vendor Status

Share

CVE-2026-22773 vulnerability details – vuln.today
Back

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy