EUVD-2026-17975
CVSS Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Lifecycle Timeline
3Tags
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.
Analysis
Remote code execution in llama.cpp RPC backend allows unauthenticated attackers with TCP access to achieve arbitrary memory read/write and full ASLR bypass. The vulnerability stems from missing bounds validation in deserialize_tensor() when processing GRAPH_COMPUTE messages with zero-valued buffer fields. …
Sign in for full analysis, threat intelligence, and remediation guidance.
Remediation
Within 24 hours: Identify all systems running llama.cpp RPC backend and isolate them from untrusted networks; document inventory with versions. Within 7 days: Implement network segmentation restricting RPC port access to trusted internal hosts only; disable RPC backend if not operationally required. …
Sign in for detailed remediation steps.
Priority Score
Share
External POC / Exploit Code
Leaving vuln.today