cvedb.io
CVE-2025-52566
HIGH · CVSS 8.6
EPSS exploitation probability: 0%
Published 2025-06-24T04:15:46.967 · Last modified 2026-06-17T09:36:41.500

Summary

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.

Affected products

ggml — llama.cpp

Does this affect you?

Add your gear to cvedb and we'll alert you only when ggml ships something exploited.

Check my exposure →

References

This product uses data from the NVD API but is not endorsed or certified by the NVD. Informational only; not professional security advice.