DirectorySecurity AdvisoriesPricing
Sign in
Security Advisories

CVE-2026-22773

NVD

https://nvd.nist.gov/vuln/detail/CVE-2026-22773

Severity

6.5

Medium

CVSS V3

Eliminate CVEs with Chainguard hardened images

Build, ship, and run secure software with minimal, hardened container images — rebuilt from source daily and guarded under our industry-leading remediation SLA.

Start for free

Summary

vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

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.

References

  • https://nvd.nist.gov/vuln/detail/CVE-2026-22773

Affected packages


The trusted source for open source

Talk to an expert
PrivacyTerms

Product

Chainguard ContainersChainguard LibrariesChainguard VMsChainguard OS PackagesChainguard ActionsChainguard Agent SkillsIntegrationsPricing
© 2026 Chainguard, Inc. All Rights Reserved.
Chainguard® and the Chainguard logo are registered trademarks of Chainguard, Inc. in the United States and/or other countries.
The other respective trademarks mentioned on this page are owned by the respective companies and use of them does not imply any affiliation or endorsement.