Vulnerabilities · 2026 · Vllm
CVE-2026-22773
Vllm vulnerability
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.
Affected products
Vllm. The exact versions are in the references.
What to do now
- Check your exposureFind out whether Vllm runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr · Exploit
- nvd.nist.gov/vuln/detail/CVE-2026-22773
- github.com/vllm-project/vllm/pull/29881
- github.com/vllm-project/vllm/commit/0ec84221718d920c3f46da879cc354f94b8fb59e
- github.com/advisories/GHSA-grg2-63fw-f2qr
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-143.yaml
- nvd.nist.gov/vuln/detail/CVE-2026-22773
- cve.org/CVERecord?id=CVE-2026-22773
More vulnerabilities in Vllm products
CVE-2026-24779CVE-2026-22807CVE-2025-66448CVE-2025-62426CVE-2025-62372CVE-2025-62164CVE-2025-59425CVE-2025-48956All 25
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.