---
cve: "CVE-2025-52566"
severity: "HIGH"
cvss: 8.6
epss: "32%"
vendor: "ggml-org"
kev: false
exploited: false
published: "2025-06-24 04:15:46"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-09-19T06:43:30+02:00"
---

# CVE-2025-52566

> 8.6 HIGH · 🧪 PoC

## Beschreibung

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-Vektor

```
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Lokal | good |
| AC Komplexität | Gering | bad |
| PR Privilegien | Keine | bad |
| UI Interaktion | Erforderlich | good |
| S Scope | Verändert | bad |
| C Vertraulichkeit | Hoch | bad |
| I Integrität | Hoch | bad |
| A Verfügbarkeit | Hoch | bad |

## Patch verfügbar (OSV)

- dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af (Commit)

## Referenzen

- <https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx>
- <https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2025-52566) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_