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.
{
"cwe_ids": [
"CWE-119",
"CWE-195"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/52xxx/CVE-2025-52566.json",
"cna_assigner": "GitHub_M"
}{
"cpe": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "b5721"
}
],
"source": [
"AFFECTED_FIELD",
"CPE_RANGE",
"REFERENCES"
]
}