Vulnerability in Vllm
CVE-2025-48887
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.
Vulnerability class: ReDoS (Regular Expression Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS 0.005, 46.0th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions >= 0.6.4, < 0.9.0
Weakness classification (CWE)
Public exploits and proof-of-concept code
Also mentioned in 1 other repository (ARPSyndicate/cve-scores). These reference the CVE in a list, notes or a scanner and are not exploit code for it.
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-w6q7-j642-7c25 (Exploit, Vendor Advisory)
- https://github.com/vllm-project/vllm/pull/18454 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/commit/4fc1bf813ad80172c1db31264beaef7d93fe0601 (Patch)