Skip to content
OpenAdvisories
Critical · 9.8 Public exploit CVE-2026-34159 EUVD-2026-17975

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

Published Apr 1, 2026 · Updated Apr 2, 2026 · Assigned by GitHub_M

Vendor: ggml-org Product: llama.cpp Package: llama.cpp Package: llama.cpp Ecosystem: Debian Ecosystem: Ubuntu

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 products

VendorProductAffectedFixed
ggml-org llama.cpp < b8492 —

Fixed in Linux distributions

Distributions backport fixes, so the version that fixes this vulnerability differs per release — upgrade to at least the version shown. From the distributions' security trackers and advisories.

Debian

Security tracker ↗
ReleasePackageFixed inAdvisory
Debian 14 llama.cpp 8611+dfsg-1 —

Ubuntu

Security tracker ↗
ReleasePackageFixed inAdvisory
Ubuntu 25.10 llama.cpp No fix yet —

Public exploits

Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.

Third-party code, not reviewed by us. Public PoCs are sometimes fake or contain malware. Read the code first and run it only in an isolated lab, against systems you are authorised to test.

GitHub 3 repositories

Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.

References