CVE-2026-43632
Publication date 7 August 2026
Last updated 7 August 2026
Ubuntu priority
Description
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.
Status
| Package | Ubuntu Release | Status |
|---|---|---|
| llama.cpp | 26.04 LTS resolute |
Needs evaluation
|
| 24.04 LTS noble | Not in release | |
| 22.04 LTS jammy | Not in release |
Severity score breakdown
CVSS version:
Base score
9.2 · Critical
Vector: CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Base score
8.1 · High
Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H