CVE-2026-65315

A flaw was found in Ollama. A remote attacker can exploit an uncontrolled memory allocation vulnerability in the GGUF metadata parser. By supplying a specially crafted GGUF file, an attacker can manipulate length and count fields, leading to excessive memory allocation. This can cause the server ...

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-2024-2169 · Unknown · Gguf Library

Name of the Vulnerable Software and Affected Versions: GGUF library version prior to the fix of Commit 18c2e17 Description: A heap-based buffer overflow vulnerability exists in the GGUF library's info-ne functionality of llama.cpp. This issue can be exploited by providing a specially crafted .ggu...

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 Input Validation Error Vulnerability

llama.cpp is a multimodal model by the individual developer Georgi Gerganov. An input validation error vulnerability exists in versions of llama.cpp prior to 18c2e17, which stems from a heap-based buffer overflow vulnerability in the gguffreadstr function in GGUF, where a specially crafted .gguf...