Strix
26.1K

CVE-2025-48887

MEDIUMCVSS 6.5/10EPSS 0.43%

Last modified

CVE-2025-48887 is a medium-severity vulnerability rated 6.5/10 on the CVSS scale. 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. EPSS estimates a 0.43% chance of exploitation in the next 30 days.

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.

Metrics

CVSS 3.1
6.5/10

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

EPSS Probability
0.43%

34.1th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

VendorProductVersions
VllmVllm>= 0.6.4, < 0.9.0

References

Timeline

Published
Last Modified
Status
Analyzed

Frequently Asked Questions

What is 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.
How severe is CVE-2025-48887?
CVE-2025-48887 has a CVSS score of 6.5/10 (MEDIUM severity). The EPSS model estimates a 0.43% probability of exploitation in the next 30 days.
How do I fix CVE-2025-48887?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

Are you affected by CVE-2025-48887?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST