| Component | llama.cpp |
| Severity | medium (CVSS 5.5) |
| CVSS vector | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H |
| Published (NVD) | 2026-10-27 |
| Last modified | 2026-10-28 |
| Affected versions | < b5649 from the CVE Program record written by the CNA that assigned the CVE |
| Fixed in | b5649 |
| Weakness | CWE-125 |
| CISA KEV | not listed |
Versions, checked against NVD
NVD's record (status: Awaiting Analysis) lists no affected versions of llama.cpp for this CVE. The ranges above come from the CVE record written by VulnCheck, the CNA that assigned the CVE.
NVD description
llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.
What to do
- Upgrade llama.cpp to
b5649or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2025-71439
- https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771
- https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac
- https://github.com/ggml-org/llama.cpp/pull/14145
- https://github.com/ggml-org/llama.cpp/releases/tag/b5649
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6
- https://www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-out-of-bounds-read-via-llama-vocab-impl-print-info