ggml 関連製品全体の CVE とセキュリティ脆弱性情報を集約し、CVSS、EPSS、公開日、脆弱性情報データを掲載しています。
一般的な弱点パターンには バッファオーバーフロー and vendor risk memory corruption があり、vendor surface software deployment and vendor surface production workloads の利用場面で vendor impact memory corruption and アプリケーションクラッシュ などのリスクが生じる可能性があります。
掲載データは公開脆弱性情報とセキュリティ公告に基づき、過去の暴露面と修補優先度の評価に利用できます。
| CVE | 概要 | ソース | CVSS 最大値 | EPSS（%） | 公開 | 更新 |
|---|---|---|---|---|---|---|
| CVE-2026-34159 | llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been pa | [email protected] | 9.8 | 0.42% | 2026-04-01 | 2026-04-30 |
| CVE-2026-33298 | llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Ex | [email protected] | 7.8 | 0.04% | 2026-03-24 | 2026-04-30 |
| CVE-2026-21869 | llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process | [email protected] | 8.8 | 0.22% | 2026-01-08 | 2026-02-02 |
| CVE-2025-52566 | llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721. | [email protected] | 8.6 | 0.23% | 2025-06-24 | 2025-08-27 |
| CVE-2025-49847 | llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicio | [email protected] | 8.8 | 0.61% | 2025-06-17 | 2025-08-27 |
| CVE-2024-42479 | llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address writing. This vulnerability is fixed in b3561. | [email protected] | 10.0 | 5.68% | 2024-08-12 | 2026-04-27 |
| CVE-2024-42478 | llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address reading. This vulnerability is fixed in b3561. | [email protected] | 5.3 | 0.49% | 2024-08-12 | 2026-04-27 |
| CVE-2024-42477 | llama.cpp provides LLM inference in C/C++. The unsafe `type` member in the `rpc_tensor` structure can cause `global-buffer-overflow`. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561. | [email protected] | 5.3 | 0.27% | 2024-08-12 | 2026-04-27 |
| CVE-2024-41130 | llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427. | [email protected] | 5.4 | 0.10% | 2024-07-22 | 2025-08-27 |
| CVE-2024-32878 | Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this uninitialized value and cause arbitrary address free problems. This may further lead to be exploited. Causes llama.cpp to crash (DoS) and may even lead to arbitrary code execution (RCE). This vulnerabili | [email protected] | 7.1 | 0.27% | 2024-04-26 | 2025-09-02 |
| CVE-2024-23605 | A heap-based buffer overflow vulnerability exists in the GGUF library header.n_kv 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. | [email protected] | 8.8 | 0.20% | 2024-02-26 | 2026-04-27 |
| CVE-2024-23496 | A heap-based buffer overflow vulnerability exists in the GGUF library gguf_fread_str 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. | [email protected] | 8.8 | 0.20% | 2024-02-26 | 2026-04-27 |
| CVE-2024-21836 | A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors 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. | [email protected] | 8.8 | 0.20% | 2024-02-26 | 2026-04-27 |
| CVE-2024-21825 | A heap-based buffer overflow vulnerability exists in the GGUF library GGUF_TYPE_ARRAY/GGUF_TYPE_STRING parsing 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. | [email protected] | 8.8 | 0.19% | 2024-02-26 | 2026-04-27 |
| 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. | [email protected] | 8.8 | 0.58% | 2024-02-26 | 2026-04-27 |