Ollama GGUF Quantization Remote Memory Leak

Overview Ollama’s model quantization engine contains a vulnerability that allows an attacker with access to the model upload interface to read and potentially exfiltrate heap memory from the server. This issue may lead to unintended behavior, including unauthorized access to sensitive data and, i...

Heap-based Buffer Overflow

Overview Affected versions of this package are vulnerable to Heap-based Buffer Overflow in the ggmlnbytes function. An attacker can achieve memory corruption and potentially execute arbitrary code by supplying a specially crafted GGUF file with manipulated tensor dimensions that trigger an intege...

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...

EUVD-2026-14668

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-2026-27940 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

Summary of CVE-2026-27940 : The llama.cpp component has a vulnerability in gguf_init_from_file_impl() within gguf.cpp where an integer overflow leads to an undersized heap allocation. This enables a subsequent fread() to write 528+ bytes of attacker-controlled data past the buffer boundary, const...

CVE-2024-39720

An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file,...

Denial Of Service (DoS)

mlx is vulnerable to Denial of Service DoS. The vulnerability is due to dereferencing an untrusted pointer from the external gguflib library in mlx::core::loadgguf without proper validation, allowing a malicious GGUF file to trigger a segmentation fault and crash the application...

CVE-2025-62609

MLX (on Apple silicon) prior to version 0.29.4 is affected by a wild pointer dereference in mlx::core::load_gguf() when loading malicious GGUF files, dereferencing an untrusted pointer from gguflib without validation and causing a crash. The issue stems from loading external GGUF data and manifes...

EUVD-2025-7036

Malicious code in bioql PyPI...

CVE-2024-21802

A heap-based buffer overflow vulnerability exists in the GGUF library info-ne functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can lead to code execution. An attacker can provide a malicious file to trigger this vulnerability...

Out-of-bounds Read

Ollama is vulnerable to Out-of-bounds Read. The vulnerability is due to the ability to upload a malformed GGUF file containing only 4 bytes with a custom magic header. By using a custom Modelfile with a FROM statement pointing to an attacker-controlled blob, the attacker can cause a segmentation...

CVE-2024-39720

An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file,...

CVE-2024-39720

An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file,...

CVE-2024-39720

An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file,...

Llama.cpp 安全漏洞

llama.cpp is a LLaMA model for inferring Meta in pure C/C++. A security vulnerability exists in Llama.cpp, which stems from an exploit of an uninitialized heap variable vulnerability in ggufinitfromfile...

CVE-2024-23605

A heap-based buffer overflow vulnerability exists in the GGUF library header.nkv functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can lead to code execution. An attacker can provide a malicious file to trigger this vulnerability...

PT-2024-1984 · Unknown · Gguf Library

Name of the Vulnerable Software and Affected Versions: GGUF library affected versions not specified Description: A heap-based buffer overflow vulnerability exists in the GGUF library's GGUF TYPE ARRAY/GGUF TYPE STRING parsing functionality of llama.cpp. This issue is related to integer overflow...

llama.cpp GGUF library header.n_kv heap-based buffer overflow vulnerability

Talos Vulnerability Report TALOS-2024-1916 llama.cpp GGUF library header.nkv heap-based buffer overflow vulnerability February 26, 2024 CVE Number CVE-2024-23605 SUMMARY A heap-based buffer overflow vulnerability exists in the GGUF library header.nkv functionality of llama.cpp Commit 18c2e17. A...

llama.cpp GGUF library info->ne heap-based buffer overflow vulnerability

Talos Vulnerability Report TALOS-2024-1914 llama.cpp GGUF library info-ne heap-based buffer overflow vulnerability February 26, 2024 CVE Number CVE-2024-21802 SUMMARY A heap-based buffer overflow vulnerability exists in the GGUF library info-ne functionality of llama.cpp Commit 18c2e17. A special...