CVE-2025-48943

Published

Last updated

NVD

https://nvd.nist.gov/vuln/detail/CVE-2025-48943

Severity

6.5

Medium

CVSS V3

Summary

vLLM allows clients to crash the openai server with invalid regex

Description

vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

References

https://images.chainguard.dev/security/CGA-4ccv-xj33-f224
https://github.com/advisories/GHSA-9hcf-v7m4-6m2j
https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff
https://github.com/vllm-project/vllm/issues/17313
https://github.com/vllm-project/vllm/pull/17623
https://github.com/vllm-project/vllm/security/advisories/GHSA-9hcf-v7m4-6m2j

Affected packages

Advisories are based on vulnerability information provided by Grype from Anchore. Learn how Chainguard creates security advisories.

CVE-2025-48943

Severity

Summary

Description

References

Affected packages

The trusted source for open source

Product

Solutions

Customers

Resources

Company