CVE-2026-70639 llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp
Attackers can cause a denial of service in Android applications using llama.cpp by supplying a corrupt model file that triggers a null pointer dereference crash.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- A user has to click or open something
- Fix
- Available
What is CVE-2026-70639?
CVE-2026-70639 is a medium-severity vulnerability in ggml-org llama.cpp, published on 6 Aug 2026. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.
Official description
llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench_1model() function fails to validate the model context pointer before dereferencing it. Attackers can supply a malicious, corrupt, or truncated model file to trigger a null context condition, causing a SIGSEGV crash that terminates the Android application process and results in denial of service.
Weakness: CWE-476
Which versions are affected by CVE-2026-70639?
It affects 1 product.
Products include Ggml Llama.cpp.
How do I fix CVE-2026-70639?
Apply the vendor's patch.
Is CVE-2026-70639 being exploited?
There is no known exploitation of CVE-2026-70639 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-2026-43632 llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
Sources
Also known as DEBIAN-CVE-2026-70639, GHSA-6xfh-c5w2-8vqf.