CVE-2025-71439

NameCVE-2025-71439
Descriptionllama.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.
SourceCVE (at NVD; CERT, ENISA, LWN, oss-sec, fulldisc, Debian ELTS, Red Hat, Ubuntu, Gentoo, SUSE bugzilla/CVE, GitHub advisories/code/issues, web search, more)

Vulnerable and fixed packages

The table below lists information on source packages.

Source PackageReleaseVersionStatus
llama.cpp (PTS)forky1:0.7.0+dfsg-2fixed
sid1:0.9.0+dfsg-1fixed

The information below is based on the following data on fixed versions.

PackageTypeReleaseFixed VersionUrgencyOriginDebian Bugs
llama.cppsource(unstable)5713+dfsg-1

Notes

https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6
https://github.com/ggml-org/llama.cpp/pull/14145
Fixed by: https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac (b5649)

Search for package or bug name: Reporting problems