CVE-2026-34159

CRITICAL

9.8

Description

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.

Details CVE

Score CVSS v3.19.8

SeveriteCRITICAL

Vecteur CVSSCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Vecteur d'attaqueNETWORK

ComplexiteLOW

Privileges requisNONE

Interaction utilisateurNONE

Publie4/1/2026

Derniere modification4/3/2026

Sourcenvd

Observations honeypot0

Faiblesses (CWE)

CWE-119

References

https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042(security-advisories@github.com)

https://github.com/ggml-org/llama.cpp/pull/20908(security-advisories@github.com)

https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw(security-advisories@github.com)

Correlations IOC

Aucune correlation enregistree

This product uses data from the NVD API but is not endorsed or certified by the NVD.