CVE-2025-48943: 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
Summary
CVE-2025-48943 is a Denial of Service vulnerability (a type of attack that crashes a system) in vLLM versions 0.8.0 through 0.8.x that causes the server to crash when given an invalid regex (a pattern used to match text). This happens specifically when using the structured output feature, which lets the AI format responses in a specific way.
Solution / Mitigation
Upgrade to version 0.9.0, which fixes the issue. A patch is available at https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff.
Vulnerability Details
6.5(medium)
EPSS: 0.1%
Classification
Taxonomy References
Affected Vendors
Related Issues
CVE-2022-29200: TensorFlow is an open source platform for machine learning. Prior to versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4, the implem
CVE-2021-29541: TensorFlow is an end-to-end open source platform for machine learning. An attacker can trigger a dereference of a null p
Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-48943
First tracked: February 15, 2026 at 08:44 PM
Classified by LLM (prompt v3) · confidence: 95%