CVE-2025-48887: vllm-project vllm

Vulnerability summary

CVE-2025-48887 is a medium (CVSS 6.5) vulnerability in vllm-project vllm. EPSS estimates a 0.52% chance of exploitation in the next 30 days, higher than 42.9% of scored vulnerabilities. 1 public exploit is recorded.

Timeline

1. 30-05-2025
   PublishedVulnerability first disclosed.
2. 30-05-2025
   Last modifiedVulnerability information updated.

Description

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.

• CWE-1333Inefficient Regular Expression ComplexityThe product uses a regular expression with a worst-case computational complexity that is inefficient and possibly exponential.