| Component | llama.cpp |
| Severity | high (CVSS 7.1) |
| CVSS vector | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:L |
| Published (NVD) | 2024-04-26 |
| Last modified | 2026-06-17 |
| Affected versions | llama.cpp >= b2715, < b2740 |
| Fixed in | b2740 |
| Weakness | CWE-456 |
| CISA KEV | not listed |
NVD description
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 vulnerability has been patched in commit b2740.
What to do
- Upgrade llama.cpp to
b2740or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2024-32878
- https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv
- https://github.com/ggerganov/llama.cpp/releases/tag/b2749
Other llama.cpp CVEs
llama.cpp before b11393 contains a use-after-free and double free vulnerability in common_chat_peg_mapper::map that allows unauthenticated r...
A vulnerability was detected in ggml-org llama.cpp up to 0.4.0. This impacts the function rpc_server::deserialize_tensor of the file ggml/sr...
llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service (std::bad_all...
llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.
llama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to-grammar.cpp, resulting in a denial of service.
A vulnerability was determined in ggml-org llama.cpp bec4772f6. This affects the function rpc_server::graph_compute of the file ggml/src/ggm...