llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
At a glance
Severity
CRITICAL 9.2
EPSS
EPSS 0.48 % · percentile 41 (2026-10-27)
State
PUBLISHED
Published
Updated
Assigner
VulnCheck
NVD status
Analyzed
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.