CVE-2026-34159 | BDVDB-2026-324200 Detail

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.

Impact#

Weaknesses#

References#

Exploit#

History#

1. Version 12026-04-01Record published in the CVE List.
2. Version 22026-04-02Most recent update recorded in the CVE List.