Lucene search
+L

694 matches found

Cvelist
Cvelist
added 2026/03/24 12:01 a.m.134 views

CVE-2026-33298 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

7.8CVSS0.00477EPSS
SaveExploits1References2
ATTACKERKB
ATTACKERKB
added 2026/03/24 12:01 a.m.15 views

CVE-2026-33298

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

7.8CVSS6.1AI score0.00477EPSS
SaveExploits1References3
CNNVD
CNNVD
added 2026/03/24 12:00 a.m.17 views

llama.cpp 输入验证错误漏洞

Llama.cpp is a multimodal model developed by Georgi Gerganov. Previous versions of llama.cpp b7824 contained a vulnerability related to input validation errors. This vulnerability stemmed from an integer overflow in the ggmlnbytes function, which could lead to a heap buffer overflow and remote co...

7.8CVSS6.3AI score0.00477EPSS
SaveExploits1References3
vulnersOsv
vulnersOsv
added 2026/03/21 12:34 p.m.4 views

cy-ai-trainer (>=0.0.1, <=0.0.2), llama-index-packs-vanna (>=0.0.1, <=0.3.0) +2 more potentially affected by CVE-2026-4513 via vanna (>=0.0.30, <=2.0.2)

vanna PYPI version =0.0.30, =0.0.1, =0.0.1, =1.4.0a20260123, =1.0.0, =2.0.0 Source cves: CVE-2026-4513 Source advisory: SNYK:PYTHON-VANNA-15756488...

6.5CVSS6.3AI score0.00196EPSS
SaveExploits0
vulnersOsv
vulnersOsv
added 2026/03/21 10:35 a.m.1 views

cy-ai-trainer (>=0.0.1, <=0.0.2), llama-index-packs-vanna (>=0.0.1, <=0.3.0) +2 more potentially affected by CVE-2026-4511 via vanna (>=0.0.30, <=2.0.2)

vanna PYPI version =0.0.30, =0.0.1, =0.0.1, =1.4.0a20260123, =1.0.0, =2.0.0 Source cves: CVE-2026-4511 Source advisory: SNYK:PYTHON-VANNA-15756186...

6.5CVSS6.3AI score0.00232EPSS
SaveExploits0
GithubExploit
GithubExploit
added 2026/03/17 12:43 p.m.166 views

aicerberus

AICerberus 🐺 AI supply chain security scanner — one comma...

6.2AI score
SaveExploits0
SUSE CVE
SUSE CVE
added 2026/03/17 12:27 a.m.10 views

SUSE CVE-2026-2069

A flaw has been found in ggml-org llama.cpp up to 55abc39. Impacted is the function llamagrammaradvancestack of the file llama.cpp/src/llama-grammar.cpp of the component GBNF Grammar Handler. This manipulation causes stack-based buffer overflow. The attack needs to be launched locally. The exploi...

4.8CVSS5.9AI score0.00124EPSS
SaveExploits0References3
vulnersOsv
vulnersOsv
added 2026/03/16 10:48 a.m.1 views

cy-ai-trainer (>=0.0.1, <=0.0.2), llama-index-packs-vanna (>=0.0.1, <=0.3.0) +2 more potentially affected by CVE-2026-4229 via vanna (>=0.0.30, <=2.0.2)

vanna PYPI version =0.0.30, =0.0.1, =0.0.1, =1.4.0a20260123, =1.0.0, =2.0.0 Source cves: CVE-2026-4229 Source advisory: SNYK:PYTHON-VANNA-15674521...

7.5CVSS7.3AI score0.00254EPSS
SaveExploits0
vulnersOsv
vulnersOsv
added 2026/03/16 10:48 a.m.2 views

cy-ai-trainer (>=0.0.1, <=0.0.2), llama-index-packs-vanna (>=0.0.1, <=0.3.0) +2 more potentially affected by CVE-2026-4231 via vanna (>=0.0.30, <=2.0.2)

vanna PYPI version =0.0.30, =0.0.1, =0.0.1, =1.4.0a20260123, =1.0.0, =2.0.0 Source cves: CVE-2026-4231 Source advisory: SNYK:PYTHON-VANNA-15674520...

7.5CVSS7.4AI score0.00278EPSS
SaveExploits0
vulnersOsv
vulnersOsv
added 2026/03/16 10:47 a.m.1 views

cy-ai-trainer (>=0.0.1, <=0.0.2), llama-index-packs-vanna (>=0.0.1, <=0.3.0) +2 more potentially affected by CVE-2026-4230 via vanna (>=0.0.30, <=2.0.2)

vanna PYPI version =0.0.30, =0.0.1, =0.0.1, =1.4.0a20260123, =1.0.0, =2.0.0 Source cves: CVE-2026-4230 Source advisory: SNYK:PYTHON-VANNA-15674519...

6.5CVSS6.3AI score0.00192EPSS
SaveExploits0
SUSE CVE
SUSE CVE
added 2026/03/13 1:16 p.m.16 views

SUSE CVE-2026-27940

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS5.9AI score0.00177EPSS
SaveExploits1References3
OSV
OSV
added 2026/03/12 5:16 p.m.4 views

DEBIAN-CVE-2026-27940

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS5.5AI score0.00177EPSS
SaveExploits1References1
NVD
NVD
added 2026/03/12 5:16 p.m.8 views

CVE-2026-27940

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS0.00177EPSS
SaveExploits1References1
OSV
OSV
added 2026/03/12 5:16 p.m.12 views

UBUNTU-CVE-2026-27940

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS6AI score0.00177EPSS
SaveExploits1References2
UbuntuCve
UbuntuCve
added 2026/03/12 5:16 p.m.9 views

CVE-2026-27940

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS5.9AI score0.00177EPSS
SaveExploits1References1
Cvelist
Cvelist
added 2026/03/12 4:39 p.m.36 views

CVE-2026-27940 llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS0.00177EPSS
SaveExploits1References1
Debian CVE
Debian CVE
added 2026/03/12 4:39 p.m.19 views

CVE-2026-27940

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS5.5AI score0.00177EPSS
SaveExploits1
OSV
OSV
added 2026/03/12 4:39 p.m.9 views

CVE-2026-27940 llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

7.8CVSS5.9AI score
SaveExploits0References3
RedhatCVE
RedhatCVE
added 2026/03/02 1:43 p.m.17 views

CVE-2026-28400

Docker Model Runner DMR is software used to manage, run, and deploy AI models using Docker. Versions prior to 1.0.16 expose a POST /engines/configure endpoint that accepts arbitrary runtime flags without authentication. These flags are passed directly to the underlying inference server llama.cpp...

7.5CVSS6.1AI score0.00226EPSS
SaveExploits0References1
NVD
NVD
added 2026/02/27 10:16 p.m.24 views

CVE-2026-28400

Docker Model Runner DMR is software used to manage, run, and deploy AI models using Docker. Versions prior to 1.0.16 expose a POST /engines/configure endpoint that accepts arbitrary runtime flags without authentication. These flags are passed directly to the underlying inference server llama.cpp...

7.5CVSS0.00226EPSS
SaveExploits0References2
Rows per page
Query Builder