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...

CVE-2026-33298

Summary (CVE-2026-33298) : llama.cpp (C/C++) contains an integer overflow in the ggml_nbytes function during GGUF tensor parsing, allowing an attacker to bypass memory validation by crafting tensor dimensions. This can cause ggml_nbytes to report a far too small size (examples cite 4 MB vs exabyt...

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...

llama.cpp: Input validation error vulnerability

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...

aicerberus

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

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...

llama-index-packs-vanna (>=0.1.5, <=0.3.0), nvidia-nat-vanna (>=1.4.0a20260123, <=1.7.0a20260513) +1 more potentially affected by CVE-2026-4229 via vanna (2.0.2)

vanna PYPI version 2.0.2 is affected by a known vulnerability. The following packages have a transitive dependency on vanna and may be impacted: - llama-index-packs-vanna =0.1.5, =1.4.0a20260123, =1.0.0, =2.0.0 Source cves: CVE-2026-4229 Source advisory: OSV:GHSA-6MJ8-JMP2-G8Q7...

llama-index-packs-vanna (>=0.0.1, <=0.1.4) potentially affected by CVE-2026-4229 via vanna (0.0.36)

vanna PYPI version 0.0.36 is affected by a known vulnerability. The following packages have a transitive dependency on vanna and may be impacted: - llama-index-packs-vanna =0.0.1, =0.1.4 Source cves: CVE-2026-4229 Source advisory: OSV:GHSA-6MJ8-JMP2-G8Q7...

llama-index-packs-vanna (>=0.1.5, <=0.3.0), nvidia-nat-vanna (>=1.4.0a20260123, <=1.7.0a20260513) +1 more potentially affected by CVE-2026-4229 via vanna (2.0.2)

vanna PYPI version 2.0.2 is affected by a known vulnerability. The following packages have a transitive dependency on vanna and may be impacted: - llama-index-packs-vanna =0.1.5, =1.4.0a20260123, =1.0.0, =2.0.0 Source cves: CVE-2026-4229 Source advisory: GHSA-6MJ8-JMP2-G8Q7...

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...

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...

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...

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...

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...

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...

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...

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...

ai-dynamo (>=0.1.0, <=0.3.0), bentoctl (0.2.3) +6 more potentially affected by CVE-2026-27905 via bentoml (>=1.0.0a7, <=1.4.8)

bentoml PYPI version =1.0.0a7, =0.1.0, =1.0.1, =0.3.12.dev20240709150559, =0.0.1, =1.0.3, =0.0.10, =0.6.30 - raptor-labsdk 0.3.2 Source cves: CVE-2026-27905 Source advisory: GHSA-M6W7-QV66-G3MF...

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...

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...