CVE-2025-52566: 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…

PriorityP342high8.8CVSS 3.1

AVNACLPRNUIRSUCHIHAH

EPSS

0.32%

23.6th percentile

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

4 ranges

Vendor	Product	Version range	Fixed in
debian	llama.cpp	< llama.cpp 5760+dfsg-1 (sid)	llama.cpp 5760+dfsg-1 (sid)
ggml-org	llama.cpp	< b5721	b5721
ggml	llama.cpp	< b5721	b5721
llama.cpp	llama.cpp	>= 0 < 5760+dfsg-1	5760+dfsg-1

CVSS provenance

nvdv3.18.8HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

osv8.8HIGH

vendor_debian8.6HIGH

Stop checking back — get the weekly exploitation signal.

Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.