CVE-2026-34159 | llama.cpp is an inference of several LLM models in C/C++. Pr… | CVSS 9.8 CRITICAL

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.

Metadata

CVE ID: CVE-2026-34159
State: PUBLISHED
Assigner: GitHub_M
Reserved: 2026-03-25 20:12 UTC
Published: 2026-04-01 16:59 UTC
Last updated: 2026-04-02 03:56 UTC
Primary CWE: CWE-119
CWE-119: Improper Restriction of Operations within the Bound…
Vendor / Product: ggml-org / llama.cpp
Sources: cve.org · NVD

Severity & Metrics

9.8 CRITICAL CVSS 3.1

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

SSVC — CISA Coordinator

Exploitation: PoC
Automatable: yes
Tech. Impact: total

Affected products (1)

Vendor	Product	Platform	Versions
ggml-org	llama.cpp	—	< b8492

Weakness (CWE)

CWE	Source	Description
CWE-119	cna	CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer

CVSS scores (1)

Score	Severity	Version	Source	Vector
9.8	CRITICAL	3.1	cna	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References (3)

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