GHSA-vfm7-4h43-gp6m
Duplicate Advisory: vLLM Vulnerable to Regular Expression Denial of Service
Withdrawn ·
At a glance
- Published
- Updated
- CVSS_V3
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
- 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
Description
### Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp.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.
Affected packages
| Package | Versions |
|---|---|
| PyPI · vllm | introduced 0.6.3, fixed 0.9.0 |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhp WEB
- https://nvd.nist.gov/vuln/detail/CVE-2025-71379 ADVISORY
- https://github.com/vllm-project/vllm PACKAGE
- https://www.vulncheck.com/advisories/vllm-regular-expression-denial-of-service-in-multiple-components WEB
Sources
| Source | Licence |
|---|---|
| OSV.dev | CC-BY 4.0 — GitHub Advisory Database |