CVE-2025-48943
vLLM allows clients to crash the openai server with invalid regex
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- Low
- User interaction
- None
What an attacker can affect
- Confidentiality
- None
- Integrity
- None
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
vLLM allows clients to crash the openai server with invalid regex
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.
- Record
CVE-2025-48943- CVSS 3.1
- 6.5 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - Weakness
- CWE-248
- Updated
- 2026-11-02
EUVDEUVD-2025-16515
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.
- Record
EUVD-2025-16515- CVSS 3.1
- 6.5 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-9hcf-v7m4-6m2j
vLLM allows clients to crash the openai server with invalid regex
Impact
A denial of service bug caused the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg, but for regex instead of a JSON schema.
Issue with more details: https://github.com/vllm-project/vllm/issues/17313
Patches
- Record
GHSA-9hcf-v7m4-6m2j- CVSS 3.1
- 6.5 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - Weakness
- CWE-248
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2025-48943- CVSS 3.1
- 6.5 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - Weakness
- CWE-248
- Updated
- 2026-11-02
OSV
vLLM allows clients to crash the openai server with invalid regex
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.
- Record
CVE-2025-48943- CVSS 3.1
- 6.5 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - Weakness
- CWE-248
- Updated
- 2026-11-11
OSVGHSA-9hcf-v7m4-6m2j
vLLM allows clients to crash the openai server with invalid regex
Impact
A denial of service bug caused the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg, but for regex instead of a JSON schema.
Issue with more details: https://github.com/vllm-project/vllm/issues/17313
Patches
- Record
GHSA-9hcf-v7m4-6m2j- CVSS 3.1
- 6.5 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - Weakness
- CWE-248
- Updated
- 2026-11-02
OSVPYSEC-2025-55 No score
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.
- Record
PYSEC-2025-55- Updated
- 2026-11-02
Affected products
Affected packages
History
| Recorded | Changed | Sources |
|---|---|---|
| facts | OSV | |
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2025-48943 is a medium vulnerability (CVSS 6.5) in Vllm, published May 28, 2025. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.51%, the 43rd percentile. Fixed in vllm 0.9.0.
References
github.com/vllm-project/vllm/security/advisories/GHSA-9hcf-v7m4-6m2j
nvd.nist.gov/vuln/detail/CVE-2025-48943