CVE-2025-48887

See a problem?
Please try reporting it to the source first.
Source
https://cve.org/CVERecord?id=CVE-2025-48887
Import Source
https://storage.googleapis.com/osv-test-cve-osv-conversion/osv-output/CVE-2025-48887.json
JSON Data
https://api.test.osv.dev/v1/vulns/CVE-2025-48887
Aliases
Related
Published
2025-05-30T17:36:16.716Z
Modified
2026-05-15T04:13:57.999250390Z
Severity
  • 6.5 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H CVSS Calculator
Summary
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
Details

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.

Database specific 
{
    "cwe_ids": [
        "CWE-1333"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/48xxx/CVE-2025-48887.json",
    "cna_assigner": "GitHub_M"
}
References

Affected packages