CVE-2025-48942

vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

CVSS v3.1

6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS v3.1

6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS

0.54% chance of exploitation in the next 30 days, 43th percentile

Published

2025-05-30

Proof-of-concept exploits (1)

• vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg

References

• CVE Record
• NVD entry

Related

• CVE-2025-46560
• CVE-2025-48887
• CVE-2025-48944
• CVE-2026-7141
• CVE-2026-9540
• CVE-2025-48935