CVE-2025-71439
CVE-2025-71439 · llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info
This page contains facts from public vulnerability sources. Check the original advisory before updating.
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.
CVSS 6.8 · Medium · EPSS 0.1%
- Published
- Updated
Stack: system
Affected products and versions
llama.cpp
- Versions
- ≥ 0, < b5649: Affected (custom)
No fix published
llama.cpp Ubuntu:26.10
- Versions
- 8681+dfsg-1
- 9721+dfsg-1ubuntu1
- 10438+dfsg-1
- 10438+dfsg-1ubuntu1
- Affected ranges
- ECOSYSTEM: (−∞, +∞)
No fix published
llama.cpp Ubuntu:26.04:LTS
- Versions
- 5882+dfsg-2
- 8064+dfsg-1ubuntu1
- 8681+dfsg-1
- Affected ranges
- ECOSYSTEM: (−∞, +∞)
No fix published
Original sources
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6
- https://github.com/ggml-org/llama.cpp/pull/14145
- https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac
- https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771
- https://github.com/ggml-org/llama.cpp/releases/tag/b5649
- https://www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-out-of-bounds-read-via-llama-vocab-impl-print-info
- https://nvd.nist.gov/vuln/detail/CVE-2025-71439