llama.cpp before b11393 contains a use-after-free and double free vulnerability in common_chat_peg_mapper::map that allows unauthenticated remote attackers to corrupt heap memory via a dangling current_tool pointer. Attackers can submit a chat_parser in a POST /completion request emitting a tool-id after a tool-close tag to crash llama-server and shape a heap write primitive.
https://github.com/ggml-org/llama.cpp/pull/29942
https://github.com/ggml-org/llama.cpp/commit/dbe4c3ed42343f0a7ba0fd7e808ffeaca404d29f
Published: 2026-10-07
Updated: 2026-10-07
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: 0.00422