CVE-2026-34159

< b8492

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all

9.8CRITICAL

CVE-2026-33298

< b7824

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggml_nbytes f

7.8HIGH

CVE-2026-27940

< b8146

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable

7.8HIGH

CVE-2026-21869

all versions

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed direct

8.8HIGH

CVE-2025-52566

< b5721

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow

8.6HIGH

CVE-2025-49847

< b5662

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can

8.8HIGH

CVE-2024-42479

< b3561

llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary addr

10.0CRITICAL

CVE-2024-42478

< b3561

llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary addr

5.3MEDIUM

CVE-2024-42477

< b3561

llama.cpp provides LLM inference in C/C++. The unsafe type member in the rpc_tensor structure can cause `global-buffer-overflo

5.3MEDIUM

CVE-2024-41130

< b3427

llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. T

5.4MEDIUM

CVE-2024-32878

>= b2715 and < b2740

Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code

7.1HIGH

CVE-2024-23605

< 2024-01-09

A heap-based buffer overflow vulnerability exists in the GGUF library header.n_kv functionality of llama.cpp Commit 18c2e17. A spe

8.8HIGH

CVE-2024-23496

< 2024-01-09

A heap-based buffer overflow vulnerability exists in the GGUF library gguf_fread_str functionality of llama.cpp Commit 18c2e17. A

8.8HIGH

CVE-2024-21836

< 2024-01-09

A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17.

8.8HIGH

CVE-2024-21825

< 2024-01-09

A heap-based buffer overflow vulnerability exists in the GGUF library GGUF_TYPE_ARRAY/GGUF_TYPE_STRING parsing functionality of ll

8.8HIGH

CVE-2024-21802

< 2024-01-09

A heap-based buffer overflow vulnerability exists in the GGUF library info-&gt;ne functionality of llama.cpp Commit 18c2e17. A spe

8.8HIGH