CVE-2025-48887

vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to cause severe performance degradation or make the service unavailable. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.

Affected

vllm-project · vllm

CVSS v3.1 GITHUB

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

EPSS

0.52% chance of exploitation in the next 30 days, 43rd percentile

Published

2025-05-30

Proof-of-concept exploits (2)

• vllm-project/vllm/security/advisories/GHSA-w6q7-j642-7c25
• advisories/GHSA-w6q7-j642-7c25

Security advisories

• vllm-project/vllm/pull/18454

References

• CVE Record
• NVD entry