Description (CNA)
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.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| ggml-org / llama.cpp | affected b7492 through b9060 |
CWE
CWE-416, CWE-367
References
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
- https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints
ADP enrichment
No English description supplied.
No references supplied.