CVE-2025-71439
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.
Does this matter?
Lower severity and no EPSS score yet. Track it; it rarely justifies an emergency change on its own.
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.
- CVSS 4.0
- 6.8 MEDIUMCVSS: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/M
- EPSS
- No score yet
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-125
- Source
- disclosure@vulncheck.com
References
- 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
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.