vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.
References
| Link | Resource |
|---|---|
| https://github.com/vllm-project/vllm/commit/2b3006076c5e9bc4cda9e03e3641388de3c5c286 | Patch |
| https://github.com/vllm-project/vllm/pull/45118 | Issue Tracking Patch |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-rwxx-mrjm-wc2m | Vendor Advisory Mitigation |
Configurations
History
07 Jul 2026, 19:03
| Type | Values Removed | Values Added |
|---|---|---|
| CVSS |
v2 : v3 : |
v2 : unknown
v3 : 7.5 |
| First Time |
Vllm
Vllm vllm |
|
| References | () https://github.com/vllm-project/vllm/commit/2b3006076c5e9bc4cda9e03e3641388de3c5c286 - Patch | |
| References | () https://github.com/vllm-project/vllm/pull/45118 - Issue Tracking, Patch | |
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-rwxx-mrjm-wc2m - Vendor Advisory, Mitigation | |
| CPE | cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* |
06 Jul 2026, 21:16
| Type | Values Removed | Values Added |
|---|---|---|
| New CVE |
Information
Published : 2026-07-06 21:16
Updated : 2026-07-07 19:03
NVD link : CVE-2026-55574
Mitre link : CVE-2026-55574
CVE.ORG link : CVE-2026-55574
JSON object : View
Products Affected
vllm
- vllm
CWE
CWE-1333
Inefficient Regular Expression Complexity