Vulnerability 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 Score
MEDIUM
Related Weaknesses (CWE)
References
- https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771
- https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752
- 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-r
FAQ
What is CVE-2025-71439?
CVE-2025-71439 is a vulnerability with a CVSS score of 5.5 (MEDIUM). 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 s...
How severe is CVE-2025-71439?
CVE-2025-71439 has been rated MEDIUM with a CVSS base score of 5.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2025-71439?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.