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.
Fix
Nothing published yet: no patch, vendor advisory or mitigation reference on NVD, no vendor advisory in the News for this CVE, not in CISA's KEV, no fixed package version. BaselineWatch does not guess at one.
Change history 5
- StatusPublished → Awaiting AnalysisNVD modified 2026-10-28 14:10
- StatusAwaiting Analysis → PublishedNVD modified 2026-10-27 00:33
- StatusPublished → Awaiting AnalysisNVD modified 2026-10-27 15:59
- StatusReceived → PublishedNVD modified 2026-10-27 00:33
- First seenCVSS 6.8NVD modified 2026-10-27 01:19
Affected (CPE criteria) 0
NVD has not attached CPE configurations yet.
References 6
- 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