Vulnerability 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.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
- https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tok
FAQ
What is CVE-2026-43632?
CVE-2026-43632 is a vulnerability with a CVSS score of 8.1 (HIGH). 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,...
How severe is CVE-2026-43632?
CVE-2026-43632 has been rated HIGH with a CVSS base score of 8.1/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-43632?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.