CVE-2026-34159
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor()
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.
CRITICAL · CVSS 9.8
EPSS 0.00534
Act now
- Public exploit or PoC is available
- SSVC automatable: yes - attacks can be scripted at scale
- CVSS base score ≥ 7.0
Sigma rules0
YARA rules0