CVE-2025-52566
highpriority · track · 35EPSS 0.004 · 30 %ileEUUSEPSS · scored 2026-10-27
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
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (2)
Products and version ranges known to be affected.
also known as (2)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (9)
External citations — patches, advisories, analysis.
- https://access.redhat.com/security/cve/cve-2025-52566cnnvd
- https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70afcnnvd
- https://github.com/ggml-org/llama.cpp/releasesPatchcnnvd
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xxcnnvd
- https://nvd.nist.gov/vuln/detail/CVE-2025-52566cnnvd
- https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70afenisa_euvd
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xxenisa_euvd
- https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70afPatchnvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan