CVE-2025-62372
vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
描述
### Summary Users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct `ndim` but incorrect `shape` (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). The issue has existed ever since we added support for image embedding inputs, i.e. #6613 (released in v0.5.5) ### Details Using image embeddings as an example: - For models that support image embedding inputs, the engine crashes when scattering the embeddings to `inputs_embeds` (mismatched shape) - For models that don't support image embedding inputs, the engine crashes when validating the inputs inside `get_input_embeddings` (validation fails). This happens because we only validate `ndim` of the tensor, but not the full shape, in input processor (via `MultiModalDataParser`). ### Impact - Denial of service by crashing the engine ### Mitigation - Use API key to limit access to trusted users. - Set `--limit-mm-per-prompt` to 0 for all non-text modalities to ban multimodal inputs, which includes multimodal embedding inputs. However, the model would then only accept text, defeating the purpose of using a multi-modal model. ### Resolution - https://github.com/vllm-project/vllm/pull/27204
如何修補 CVE-2025-62372
要修補 CVE-2025-62372,請將受影響套件升級到下列已修補版本。
- —升級至 0.11.1 或更新版本
CVE-2025-62372 正在被利用嗎?
低 — EPSS 為 0.4%,目前沒有觀察到大規模利用活動。
受影響套件(1)
- >= 0.5.5, < 0.11.1
CVSS 分數
| 來源 |
|---|