CVE-2026-22773
MEDIUM6.5EPSS 0.02%vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions
發布日:2026/1/13修改日:2026/5/20
描述
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.
受影響套件(2)
CVSS 分數
| 來源 | 版本 | 嚴重程度 | 向量 |
|---|---|---|---|
| osv | CVSS 3.1 | MEDIUM6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
參考連結(5)
- ADVISORYhttps://nvd.nist.gov/vuln/detail/CVE-2026-22773
- PATCHhttps://github.com/vllm-project/vllm
- WEBhttps://github.com/vllm-project/vllm/commit/0ec84221718d920c3f46da879cc354f94b8fb59e
- WEBhttps://github.com/vllm-project/vllm/pull/29881
- WEBhttps://github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr