PYSEC-2025-54

vendorUSosv

view advisory published 2025-05-30Licence: CC-BY-4.0

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.

describes (1)

Related CVEs.

ID	severity	EPSS	exploitable	published
CVE-2025-48942US	—	0.57% (47th)	—	2025-05-30
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 a…

references

External citations — patches, advisories, analysis.

https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ffFIX
https://github.com/vllm-project/vllm/issues/17248REPORT
https://github.com/vllm-project/vllm/pull/17623REPORT
https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xgEVIDENCE

scry

Advisories like this name the exposed products attackers go after on your perimeter. See what is exposed on your perimeter with a free passive scan.

Free scan