Ggml

29 CVEs across 1 Ggml products. Browse Ggml vulnerabilities, severities, and proof-of-concept exploits.

Ggml products with known CVEs

ProductCVEs
Llama.cpp29
Ggml CVEs — newest first
CVESeverityScorePublishedSummary
CVE-2026-52132High7.52026-09-01llama.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-2026-52131High7.52026-09-01llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.
CVE-2026-52130High7.52026-09-01llama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to-grammar.cpp, resulting in a denial of service.
CVE-2026-70640High7.02026-08-06llama.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-2026-70639Medium5.52026-08-06llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench_1model() function fails…
CVE-2026-70638High7.82026-08-06llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies size…
CVE-2026-43632High8.12026-08-06llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detok…
CVE-2026-43631High8.12026-08-06llama.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-2026-43630Medium6.52026-08-06llama.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-2026-43629High8.12026-08-06llama.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-2026-43628High7.82026-08-06llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers…
CVE-2026-43627High7.82026-08-06llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llama_batch_init() function where unchecked multiplications in malloc() c…
CVE-2026-43622High7.82026-08-06llama.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-2026-34159Critical9.82026-04-01llama.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-2026-33298High7.82026-03-24llama.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-2026-27940High7.82026-03-12llama.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-2026-21869High8.82026-01-08llama.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-2025-52566High8.62025-06-24llama.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-2025-49847High8.82025-06-17llama.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-2024-42479Critical10.02024-08-12llama.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-2024-42478Medium5.32024-08-12llama.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-2024-42477Medium5.32024-08-12llama.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-2024-41130Medium5.42024-07-22llama.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-2024-32878High7.12024-04-26Llama.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-2024-23605High8.82024-02-26A 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-2024-23496High8.82024-02-26A 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-2024-21836High8.82024-02-26A 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-2024-21825High8.82024-02-26A 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-2024-21802High8.82024-02-26A heap-based buffer overflow vulnerability exists in the GGUF library info->ne functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can…