Cyber Resilience

CVE-2025-48942

MediumPublic PoC

Published: 30 May 2025

Published
30 May 2025
Modified
24 June 2025
KEV Added
—
Patch
—
CVSS Score v3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS Score 0.0021 43.5th percentile
Risk Priority 13 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-48942 is a medium-severity Uncaught Exception (CWE-248) vulnerability in Vllm Vllm. Its CVSS base score is 6.5 (Medium).

Operationally, ranked at the 43.5th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Data-Related Vulnerabilities risk domain.

EU & UK References

Vulnerability details

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…

more

GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

CWE(s)
CWE-248

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Data-Related Vulnerabilities
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llms, vllm

Related Threats

Affected Assets

vllm
vllm
0.8.0 — 0.9.0

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

SC-24 Fail in Known State
addresses: CWE-248

Prevents abrupt termination from uncaught exceptions by requiring a defined, preserved-state failure mode.

SI-17 Fail-safe Procedures
addresses: CWE-248

Requires pre-defined safe responses for uncaught exceptions so they do not result in undefined or insecure program termination.

References