CVE-2026-22773 | vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

Exp

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.

Published: 2026-01-10 Last update: 2026-01-27 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-22773 is rated Exploit Available (52.5/100): CVSS Medium severity, with low exploitation likelihood (EPSS 0.40%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2026-22773

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2026-22773

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-06-15 0.02% 0.40% +0.38%
2 2026-02-18 0.05% 0.02% -0.04%
3 2026-02-11 — 0.05% —

Full EPSS history (4 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-22773

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
6.5 3.1 MEDIUM
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:N)
Doesn’t really leak secrets in a meaningful way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 2.8 3.6 [email protected]
7.5 3.1 HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:N)
Doesn’t really leak secrets in a meaningful way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 3.6 [email protected]

Weakness enumeration for CVE-2026-22773

GitHub Security Advisory for CVE-2026-22773

GHSA-grg2-63fw-f2qr · Severity: medium · Ecosystem: pip — vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

OS Trackers for CVE-2026-22773

vendor priority summary link
redhat medium — https://access.redhat.com/security/cve/CVE-2026-22773

Affected software / configurations for CVE-2026-22773

Vendor Product Version Raw CPE
vllm vllm >= 0.6.4, < 0.12.0 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

References for CVE-2026-22773

cvelogic Threat Intelligence