CVE-2026-34159

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.

Weakness classification

• security-advisories@github.com: CWE-119

Primary references

• security-advisories@github.com — Patch
• security-advisories@github.com — Issue Tracking, Patch
• security-advisories@github.com — Exploit, Vendor Advisory