Lucene search
+L

4 matches found

NVD
NVD
•added 2026/11/20 1:18 p.m.•6 views

CVE-2026-133710

llama.cpp b11003 before b12556 contains an integer overflow in the hrmtext loader loadarchhparams that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing loadarchtensors to write tensor...

8.5CVSS0.00313EPSS
SaveExploits0References5
Cvelist
Cvelist
•added 2026/11/20 12:17 p.m.•43 views

CVE-2026-133710 llama.cpp b11003 before b12556 Heap Out-of-Bounds Write via hrm_text Model Loader

llama.cpp b11003 before b12556 contains an integer overflow in the hrmtext loader loadarchhparams that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing loadarchtensors to write tensor...

8.5CVSS0.00313EPSS
SaveExploits0References5
EUVD
EUVD
•added 2026/11/20 12:17 p.m.•8 views

EUVD-2026-131537

llama.cpp b11003 before b12556 contains an integer overflow in the hrmtext loader loadarchhparams that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing loadarchtensors to write tensor...

8.5CVSS6.5AI score0.00313EPSS
SaveExploits0References5
CVE
CVE
•added 2026/11/20 12:17 p.m.•17 views

CVE-2026-133710

The llama.cpp library (versions b11003 before b12556 ) is vulnerable to a Heap Out-of-Bounds Write via the hrm_text model loader. The root cause is an integer overflow in the load_arch_hparams() function, which allows attackers to bypass block count checks using crafted GGUF metadata . By supplyi...

8.5CVSS6.5AI score0.00313EPSS
SaveExploits0References5
Rows per page
Query Builder