CVE-2026-43632
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints
CVSS
8.1
Alto
EPSS
—
KEV
—
Exploit Today
—
0-100
Publicado: 6 ago 2026 · Última mod.: 6 ago 2026 · CWE-367 · CWE-416
Sin historial EPSS suficiente todavía.
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.