Lucene search
+L

3 matches found

RedhatCVE
RedhatCVE
added 2026/07/08 5:30 a.m.10 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
ATTACKERKB
ATTACKERKB
added 2026/07/06 8:5 p.m.10 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...

8.7CVSS5.9AI score0.00324EPSS
SaveExploits0References4Affected Software1
Github Security Blog
Github Security Blog
added 2026/03/05 6:20 p.m.10 views

xgrammar vulnerable to DoS via multi-layer nesting

Summary The multi-level nested syntax caused a segmentation fault core dump. Details A trigger stack overflow or memory exhaustion was caused by constructing a malicious grammar rule containing 30,000 layers of nested parentheses. PoC !/usr/bin/env python3 """ XGrammar - Math Expression Generatio...

8.7CVSS5.9AI score0.00706EPSS
SaveExploits1References4Affected Software1
Rows per page
Query Builder