CVE-2026-43632 llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
Attackers can trigger a use-after-free in llama-server tokenization endpoints via a race condition, potentially causing crashes or code execution when idle sleep is enabled.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-43632?
CVE-2026-43632 is a critical use after free vulnerability in ggml-org llama.cpp, published on 6 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Which versions are affected by CVE-2026-43632?
It affects 1 product.
Products include Ggml Llama.cpp.
How do I fix CVE-2026-43632?
No fix has been published for CVE-2026-43632 yet. Limit exposure of the affected software until one is available.
Upgrade to the fixed version. These bugs are found with fuzzing and sanitisers and avoided by memory-safe languages. More about Use after free.
Is CVE-2026-43632 being exploited?
There is no known exploitation of CVE-2026-43632 in the wild and no public exploit code.
Other vulnerabilities in ggml-org llama.cpp
- CVE-2024-42479 llama.cpp allows write-what-where in rpc_server::set_tensor
- CVE-2026-34159 llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
- CVE-2026-43629 llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore
- CVE-2026-43631 llama.cpp b7492–b9060 Use-After-Free RCE via llama-server
- CVE-2026-21869 llama.cpp has Out-of-bounds Write in llama-server
Sources
Also known as DEBIAN-CVE-2026-43632, GHSA-3f2h-96vw-c84x, UBUNTU-CVE-2026-43632.