Llama.cpp
by Ggml
Source repositories
CVEs (26)
| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2024-42478 | Med | 0.27 | 5.3 | 0.01 | Aug 12, 2024 | 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. | ||
| CVE-2024-42477 | Med | 0.27 | 5.3 | 0.00 | Aug 12, 2024 | 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. | ||
| CVE-2026-18581 | Low | 0.21 | 3.3 | 0.00 | Aug 3, 2026 | A vulnerability was determined in ggml-org llama.cpp e15efe0. Affected by this issue is some unknown functionality of the file common/jinja/parser.cpp of the component Jinja Minja Template Parser. Executing a manipulation with the input {{9|9|{ can lead to reachable assertion.… | ||
| CVE-2026-2069 | Low | 0.21 | 3.3 | 0.00 | Feb 6, 2026 | A flaw has been found in ggml-org llama.cpp up to 55abc39. Impacted is the function llama_grammar_advance_stack of the file llama.cpp/src/llama-grammar.cpp of the component GBNF Grammar Handler. This manipulation causes stack-based buffer overflow. The attack needs to be… | ||
| CVE-2025-52566 | Hig | 0.00 | 8.6 | 0.00 | Jun 24, 2025 | 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… | ||
| CVE-2025-49847 | Hig | 0.00 | 8.8 | 0.00 | Jun 17, 2025 | 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:… |
- risk 0.27cvss 5.3epss 0.01
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.
- risk 0.27cvss 5.3epss 0.00
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.
- risk 0.21cvss 3.3epss 0.00
A vulnerability was determined in ggml-org llama.cpp e15efe0. Affected by this issue is some unknown functionality of the file common/jinja/parser.cpp of the component Jinja Minja Template Parser. Executing a manipulation with the input {{9|9|{ can lead to reachable assertion.…
- risk 0.21cvss 3.3epss 0.00
A flaw has been found in ggml-org llama.cpp up to 55abc39. Impacted is the function llama_grammar_advance_stack of the file llama.cpp/src/llama-grammar.cpp of the component GBNF Grammar Handler. This manipulation causes stack-based buffer overflow. The attack needs to be…
- risk 0.00cvss 8.6epss 0.00
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…
- risk 0.00cvss 8.8epss 0.00
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:…
Page 2 of 2