CVE-2025-71439
llama.cpp before b5649 contains a heap out-of-bounds read …
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 now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771
- github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac
- github.com/ggml-org/llama.cpp/pull/14145
- github.com/ggml-org/llama.cpp/releases/tag/b5649
- github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6
- www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-out-of-bounds-read-via-llama-voca
- nvd.nist.gov/vuln/detail/CVE-2025-71439
- cve.org/CVERecord?id=CVE-2025-71439
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.