PoC Index

CVE-2025-52566

HIGH 8.8EPSS 0.3%

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.

CVSS v3.1
8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CVSS v3.1
8.6 HIGHCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
EPSS
0.32% chance of exploitation in the next 30 days, 24th percentile
Published
2025-06-24

Proof-of-concept exploits (1)

References

Related