GHSA-vfm7-4h43-gp6m
Suggest an improvement- Source
- https://github.com/advisories/GHSA-vfm7-4h43-gp6m
- Import Source
- https://github.com/github/advisory-database/blob/main/advisories/github-reviewed/2026/06/GHSA-vfm7-4h43-gp6m/GHSA-vfm7-4h43-gp6m.json
- JSON Data
- https://api.osv.dev/v1/vulns/GHSA-vfm7-4h43-gp6m
- Withdrawn
- 2026-09-11T15:45:34Z
- Published
- 2026-06-20T21:31:21Z
- Modified
- 2026-09-11T16:02:22Z
- Severity
-
- 4.3 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L CVSS Calculator
- 5.3 (Medium) CVSS_V4 - CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N CVSS Calculator
- Summary
- Duplicate Advisory: vLLM Vulnerable to Regular Expression Denial of Service
- Details
-
Duplicate Advisory
This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp. This link is maintained to preserve external references.
Original Description
vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service.
- Database specific
{ "cwe_ids": [ "CWE-1333" ], "github_reviewed": true, "github_reviewed_at": "2026-09-11T15:45:34Z", "nvd_published_at": "2026-06-20T19:16:23Z", "severity": "MODERATE" }- References
Affected packages
PyPI / vllm
Package
- Name
- vllm
- View open source insights on deps.dev
- Purl
- pkg:pypi/vllm