---
cve: "CVE-2026-34159"
severity: "CRITICAL"
cvss: 9.8
epss: "1.1%"
vendor: "ggml-org"
kev: false
exploited: false
published: "2026-04-01 18:16:29"
tags: [cve, security, critical]
source: tsecurity.de CVE-Dossier
exported: "2026-09-19T03:42:56+02:00"
---

# CVE-2026-34159

> 9.8 CRITICAL · 🧪 PoC

## Beschreibung

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.

## CVSS-Vektor

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

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

## Patch verfügbar (OSV)

- 39bf0d3c6a95803e0f41aaba069ffbee26721042 (Commit)

## Referenzen

- <https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw>
- <https://github.com/ggml-org/llama.cpp/pull/20908>
- <https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-34159) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_