CVE-2026-52132 | High | 7.5 | 2026-09-01 | llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service (std::bad_alloc and HTTP 500) vi… |
CVE-2026-52131 | High | 7.5 | 2026-09-01 | llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function. |
CVE-2026-52130 | High | 7.5 | 2026-09-01 | llama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to-grammar.cpp, resulting in a denial of service. |
CVE-2026-70640 | High | 7.0 | 2026-08-06 | llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench_1model() and free_1cont… |
CVE-2026-70639 | Medium | 5.5 | 2026-08-06 | llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench_1model() function fails… |
CVE-2026-70638 | High | 7.8 | 2026-08-06 | llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies size… |
CVE-2026-43632 | High | 8.1 | 2026-08-06 | llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detok… |
CVE-2026-43631 | High | 8.1 | 2026-08-06 | llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feat… |
CVE-2026-43630 | Medium | 6.5 | 2026-08-06 | llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write ac… |
CVE-2026-43629 | High | 8.1 | 2026-08-06 | llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function compu… |
CVE-2026-43628 | High | 7.8 | 2026-08-06 | llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers… |
CVE-2026-43627 | High | 7.8 | 2026-08-06 | llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llama_batch_init() function where unchecked multiplications in malloc() c… |
CVE-2026-43622 | High | 7.8 | 2026-08-06 | llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1batch() allocates memory using malloc() wh… |
CVE-2026-34159 | Critical | 9.8 | 2026-04-01 | 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 ten… |
CVE-2026-33298 | High | 7.8 | 2026-03-24 | 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… |
CVE-2026-27940 | High | 7.8 | 2026-03-12 | 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 to an Integer overflow, lead… |
CVE-2026-21869 | High | 8.8 | 2026-01-08 | 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 lla… |
CVE-2025-52566 | High | 8.6 | 2025-06-24 | 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 impl… |
CVE-2025-49847 | High | 8.8 | 2025-06-17 | 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 l… |
CVE-2024-42479 | Critical | 10.0 | 2024-08-12 | llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address writing. This vulnerabili… |
CVE-2024-42478 | Medium | 5.3 | 2024-08-12 | llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address reading. This vulnerabili… |
CVE-2024-42477 | Medium | 5.3 | 2024-08-12 | 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 le… |
CVE-2024-41130 | Medium | 5.4 | 2024-07-22 | 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… |
CVE-2024-32878 | High | 7.1 | 2024-04-26 | 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… |
CVE-2024-23605 | High | 8.8 | 2024-02-26 | 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… |
CVE-2024-23496 | High | 8.8 | 2024-02-26 | 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… |
CVE-2024-21836 | High | 8.8 | 2024-02-26 | A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf fil… |
CVE-2024-21825 | High | 8.8 | 2024-02-26 | 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 spe… |
CVE-2024-21802 | High | 8.8 | 2024-02-26 | 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… |