Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2025-48887— vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

Quick assessment

Affected
vllm-project vllm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.6.4至0.9.0之前版本存在安全漏洞，该漏洞源于工具调用检测中使用的复杂正则表达式可能导致正则表达式拒绝服务。

CVSS 6.5 · Medium EPSS 0.52% · P42

Possible ATT&CK Techniques 1 AI

T1499 · Endpoint Denial of Service
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-48887

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
CWE-1333
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.6.4至0.9.0之前版本存在安全漏洞，该漏洞源于工具调用检测中使用的复杂正则表达式可能导致正则表达式拒绝服务。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vllm >= 0.6.4, < 0.9.0 -

II. Public POCs for CVE-2025-48887

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2025-48887

请登录查看更多情报信息。

Patches & Fixes for CVE-2025-48887 (1)

Same Patch Batch · vllm-project · 2025-05-30 · 4 CVEs total

CVE-2025-48944 6.5 MEDIUM vLLM Tool Schema allows DoS via Malformed pattern and type Fields
CVE-2025-48942 6.5 MEDIUM vLLM DOS: Remotely kill vllm over http with invalid JSON schema
CVE-2025-48943 6.5 MEDIUM vLLM allows clients to crash the openai server with invalid regex

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-1333

V. Comments for CVE-2025-48887

No comments yet

Leave a comment