# CVE-2025-52566

## Summary

- **CVE ID:** CVE-2025-52566
- **Severity:** HIGH
- **CVSS Score:** 8.6 (CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H)
- **CWE:** CWE-119, CWE-195
- **Published:** Jun 24, 2025
- **Last Modified:** Mar 13, 2026

## Description

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 Products

- ggml-org — llama.cpp (< b5721)

## References

- [CNA](https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx)
- [CNA](https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.32%
- **EPSS Percentile:** 24.4

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-10._