CVE-2026-43629 llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore
Attackers with write access to state directories can trigger heap overflows in llama.cpp, potentially leading to arbitrary code execution.
- 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-2026-43629?
CVE-2026-43629 is a critical memory corruption 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 b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access to the slot_save_path directory to corrupt heap memory. Attackers can craft malicious state files where cell_count multiplication overflows or exceeds tensor buffer allocation to write attacker-controlled bytes past buffer boundaries, potentially resulting in heap metadata corruption, model weight corruption, or arbitrary code execution via function pointer overwrite.
Which versions are affected by CVE-2026-43629?
It affects 1 product.
Products include Ggml Llama.cpp.
How do I fix CVE-2026-43629?
No fix has been published for CVE-2026-43629 yet. Limit exposure of the affected software until one is available.
Upgrade to the fixed version. Memory-safe languages, compiler hardening and fuzzing prevent most new cases. More about Memory corruption.
Is CVE-2026-43629 being exploited?
There is no known exploitation of CVE-2026-43629 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-2026-43631 llama.cpp b7492–b9060 Use-After-Free RCE via llama-server
- CVE-2026-43632 llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
- CVE-2026-21869 llama.cpp has Out-of-bounds Write in llama-server
Sources
Also known as DEBIAN-CVE-2026-43629, GHSA-7p8h-8h8j-472c, UBUNTU-CVE-2026-43629.