CVE-2025-62372

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).

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

• Denial of service by crashing the engine

CVE-2025-62372 has a CVSS score of 6.5 (High). The vector is network-reachable, low privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.11.1); upgrading removes the vulnerable code path.

Kodem intelligence

1. What is CVE-2025-62372? CVE-2025-62372 is a high-severity security vulnerability in vllm (pip), affecting versions >= 0.5.5, < 0.11.1. It is fixed in 0.11.1.
2. How severe is CVE-2025-62372? CVE-2025-62372 has a CVSS score of 6.5 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
3. Which versions of vllm are affected by CVE-2025-62372? vllm (pip) versions >= 0.5.5, < 0.11.1 is affected.
4. Is there a fix for CVE-2025-62372? Yes. CVE-2025-62372 is fixed in 0.11.1. Upgrade to this version or later.
5. Is CVE-2025-62372 exploitable, and should I be worried? Whether CVE-2025-62372 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
6. What actually determines whether CVE-2025-62372 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
7. How do I fix CVE-2025-62372? Upgrade vllm to 0.11.1 or later.