llama.cpp before b8585 contains a use-after-free vulnerability in the RPC server's GRAPH_RECOMPUTE handler that allows unauthenticated remote attackers to achieve arbitrary read and write access by storing a computation graph, freeing referenced buffers, and reclaiming freed memory with attacker-controlled content. Attackers can send RPC requests to trigger re-execution of stored graphs with dangling pointers, enabling full remote code execution without requiring authentication or user interaction.
https://www.vulncheck.com/advisories/llama-cpp-use-after-free-in-rpc-graph-recompute-handler
https://github.com/ggml-org/llama.cpp/releases/tag/b8585
https://github.com/ggml-org/llama.cpp/pull/21175
https://github.com/ggml-org/llama.cpp/commit/389c7d4955ba55c7418afaebf7c23d9ed64ef707
Published: 2026-08-21
Updated: 2026-08-21
Base Score: 7.6
Vector: CVSS2#AV:N/AC:H/Au:N/C:C/I:C/A:C
Severity: High
Base Score: 8.1
Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Severity: High
Base Score: 9.2
Vector: CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Severity: Critical
EPSS: 0.00769