CVEvulnerability
CVE-2025-71439
6.8 MEDIUM
Official page ↗
- Status
- Awaiting Analysis
- Published
- 2026-10-27
- Last modified
- 2026-10-28
- Assigner
- [email protected]
- CVSS 4.0 ([email protected])
- 6.8 MEDIUM — CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
- CVSS 3.1 ([email protected])
- 5.5 MEDIUM — CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-125
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.
Related
Weakness · CWE (1)
- CWE-125 Out-of-bounds Read weakness
References
- https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771 github.com
- https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac github.com
- https://github.com/ggml-org/llama.cpp/pull/14145 github.com
- https://github.com/ggml-org/llama.cpp/releases/tag/b5649 github.com
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6 github.com
- https://www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-out-of-bounds-read-via-llama-vocab-impl-print-info www.vulncheck.com