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.

CVE Details

CVSS v3.1 Score9.8

SeverityCRITICAL

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

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionNONE

Published4/1/2026

Last Modified4/3/2026

Sourcenvd

Honeypot Sightings0

Weaknesses (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)

IOC Correlations

No correlations recorded

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