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.
Metrics
CVSS 3.1 8.1/10
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| ggml-org | llama.cpp | >= b7492, <= b9060 |
References
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patchesPatch, Third Party Advisory
- https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpointsPatch, Third Party Advisory
Timeline
- Published
- Aug 6, 2026
- Last modified
- Oct 23, 2026
- NVD status
- Analyzed