CVE-2026-43632
highpriority · track · 0EPSS 0.005 · 41 %ileEUUSEPSS · scored 2026-10-27
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
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · high–critical · 7.2–9.2
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (2)
Products and version ranges known to be affected.
also known as (3)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (6)
External citations — patches, advisories, analysis.
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patchescnnvd
- https://github.com/ggml-org/llama.cpp/releasesPatchcnnvd
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patchesenisa_euvd
- https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpointsenisa_euvd
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patchesPatchThird Party Advisorynvd
- https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpointsPatchThird Party Advisorynvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan