llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary address writing. This vulnerability is fixed in b3561.
Exploitability
AV:NAC:LPR:NUI:NScope
S:CImpact
C:HI:HA:H10/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:HOther