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() 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.

• https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042
• https://github.com/ggml-org/llama.cpp/pull/20908
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw