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
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 fin
Affected packages
- llama.cpp
Exploit signal
- Known exploited (CISA KEV)
- No
- EPSS score
- —
- EPSS percentile
- —
EPSS is the probability a CVE is exploited in the wild; percentile is its rank among all CVEs.
Sources
- https://www.cve.org/CVERecord?id=CVE-2026-43632
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
Structured record: https://ubuntu.com/security/CVE-2026-43632
Recommended response stack
Some links are affiliate links — HackTribune may earn a commission at no extra cost to you.
Get incidents like this as alerts for your stack.
Join the beta