OESA-2025-2372

See a problem?
Please try reporting it to the source first.
Source
https://www.openeuler.org/en/security/security-bulletins/detail/?id=openEuler-SA-2025-2372
Import Source
https://repo.openeuler.org/security/data/osv/OESA-2025-2372.json
JSON Data
https://api.osv.dev/v1/vulns/OESA-2025-2372
Upstream
Published
2025-10-11T13:20:09Z
Modified
2025-10-11T14:02:50.206234Z
Summary
llama.cpp security update
Details

Security Fix(es):

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.(CVE-2025-52566)

Database specific 
{
    "severity": "High"
}
References

Affected packages

openEuler:24.03-LTS-SP2 / llama.cpp

Package

Name
llama.cpp
Purl
pkg:rpm/openEuler/llama.cpp&distro=openEuler-24.03-LTS-SP2

Affected ranges

Type
ECOSYSTEM
Events
Introduced
0Unknown introduced version / All previous versions are affected
Fixed
20230815-5.oe2403sp2

Ecosystem specific 

{
    "src": [
        "llama.cpp-20230815-5.oe2403sp2.src.rpm"
    ],
    "aarch64": [
        "llama.cpp-20230815-5.oe2403sp2.aarch64.rpm"
    ],
    "x86_64": [
        "llama.cpp-20230815-5.oe2403sp2.x86_64.rpm"
    ]
}

Database specific

source 
"https://repo.openeuler.org/security/data/osv/OESA-2025-2372.json"