Lucene search
+L

10 matches found

EUVD
EUVD
added 2026/07/17 5:10 p.m.9 views

EUVD-2026-41924

vLLM: ReDoS via structuredoutputs.regex compiled without timeout in xgrammar and outlines backends...

8.7CVSS5.2AI score0.00324EPSS
SaveExploits0References5
OSV
OSV
added 2026/07/17 5:10 p.m.7 views

GHSA-RWXX-MRJM-WC2M vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends

Summary The structuredoutputs.regex API parameter passes a user-supplied regex string directly to grammar compiler backends with no compilation timeout. In the xgrammar backend, the string reaches compileregex with no guard. In the outlines backend, validateregexisbuildable blocks structural issu...

8.7CVSS5.2AI score0.00324EPSS
SaveExploits0References6
RedhatCVE
RedhatCVE
added 2026/07/08 5:30 a.m.7 views

CVE-2026-55574

A flaw was found in vLLM, a high-throughput and memory-efficient inference and serving engine for large language models LLMs. A remote attacker could exploit this vulnerability by providing a specially crafted regular expression to the structuredoutputs.regex API parameter. This adversarial regex...

8.7CVSS5.9AI score0.00324EPSS
SaveExploits0References6
NVD
NVD
added 2026/07/06 9:16 p.m.13 views

CVE-2026-55574

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structuredoutputs.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 stri...

8.7CVSS0.00324EPSS
SaveExploits0References3
OSV
OSV
added 2026/07/06 9:16 p.m.4 views

PYSEC-2026-2304

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structuredoutputs.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 stri...

7.5CVSS6.1AI score0.00324EPSS
SaveExploits0References3
CVE
CVE
added 2026/07/06 8:5 p.m.27 views

CVE-2026-55574

CVE-2026-55574 affects vLLM prior to 0.24.0, where structured_outputs.regex passes an unguarded user-supplied regex to grammar backends (xgrammar and outlines). In xgrammar, the string reaches the regex compiler without a timeout guard; in outlines, validation overlooks regex complexity (e.g., ne...

8.7CVSS5.9AI score0.00324EPSS
SaveExploits0References3Affected Software1
OSV
OSV
added 2026/07/06 8:5 p.m.5 views

CVE-2026-55574 vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structuredoutputs.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 stri...

8.7CVSS5.9AI score0.00324EPSS
SaveExploits0References5
Cvelist
Cvelist
added 2026/07/06 8:5 p.m.41 views

CVE-2026-55574 vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structuredoutputs.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 stri...

8.7CVSS0.00324EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
added 2026/07/06 12:0 a.m.16 views

PT-2026-56000

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.24.0 Description The structured outputs.regex API parameter allows user-supplied regular expression strings to be passed to grammar compiler backends without a compilation timeout. In the xgrammar backend, the string i...

8.7CVSS6AI score0.00324EPSS
SaveExploits0References12
Spring Security Advisories
Spring Security Advisories
added 2024/08/09 12:0 a.m.129 views

Spring AI Embraces OpenAI's Structured Outputs: Enhancing JSON Response Reliability

OpenAI recently introduced a powerful feature called Structured Outputs, which ensures that AI-generated responses adhere strictly to a predefined JSON schema. This feature significantly improves the reliability and usability of AI-generated content in real-world applications. Today, we're excite...

7AI score
SaveExploits0
Rows per page
Query Builder