CVEvulnerability

CVE-2026-34159

9.8 CRITICAL Published 2026-04-01 Modified 2026-10-26 Official page ↗
Status
Analyzed
Published
2026-04-01
Last modified
2026-10-26
Assigner
[email protected]
CVSS 3.1 ([email protected])
9.8 CRITICAL — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weaknesses
CWE-119

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.

Affected configurations

• ggml llama.cpp (< b8492)

Related

Weakness · CWE (1)

  • CWE-119 Improper Restriction of Operations within the Bounds of a Memory Buffer weakness

References