CVE-2026-22773
Last modified
CVE-2026-22773 is a high-severity vulnerability rated 7.5/10 on the CVSS scale. 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. EPSS estimates a 0.40% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.6.4, < 0.12.0 |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qrExploit, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-22773?
How severe is CVE-2026-22773?
How do I fix CVE-2026-22773?
Are you affected by CVE-2026-22773?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST