CVE-2026-34159

llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend

State
Published
Severity
9.8 Critical
Published
Apr 1, 2026
Updated
Apr 2, 2026
Reserved
Mar 25, 2026

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
3.19.8 CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HGitHub_M

Weaknesses

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

Affected Products

ProductVersions
llama.cppggml-org
  • < b8492Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.