---
cve: "CVE-2026-27940"
severity: "HIGH"
cvss: 7.8
epss: "18%"
vendor: "ggml-org"
kev: false
exploited: false
published: "2026-03-12 17:16:49"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-09-19T18:14:51+02:00"
---

# CVE-2026-27940

> 7.8 HIGH · 🧪 PoC

## Beschreibung

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.

## CVSS-Vektor

```
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/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 | Unverändert | good |
| C Vertraulichkeit | Hoch | bad |
| I Integrität | Hoch | bad |
| A Verfügbarkeit | Hoch | bad |

## Patch verfügbar (OSV)

- 418dea39cea85d3496c8b04a118c3b17f3940ad8 (Commit)

## Referenzen

- <https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-27940) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_