VULNERABILITY INTELLIGENCE
CVE-2026-43632
CVSS score8.1 HIGH
EPSS probability0.48%
CISA KEVNot currently listed
Published2026-08-06
Last modified2026-10-23
CVSS vectorCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
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.
Weakness classification
- disclosure@vulncheck.com: CWE-367
Primary references
- disclosure@vulncheck.com — Patch, Third Party Advisory
- disclosure@vulncheck.com — Patch, Third Party Advisory