CVE-2026-43630 llama.cpp b4882-b8487 Out-of-Bounds Read Information Disclosure
Attackers with write access to slot directories can trigger out-of-bounds reads to leak heap data and defeat ASLR in llama.cpp.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-43630?
CVE-2026-43630 is a medium-severity 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 before b8487 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with an oversized seq_id value to trigger an out-of-bounds read that leaks heap data including pointer values into server logs, defeating ASLR protections and facilitating further exploitation.
Which versions are affected by CVE-2026-43630?
It affects 1 product.
Products include Ggml Llama.cpp.
How do I fix CVE-2026-43630?
Apply the vendor's patch.
Is CVE-2026-43630 being exploited?
There is no known exploitation of CVE-2026-43630 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-2026-43630, GHSA-27j8-r4f8-8v3x, UBUNTU-CVE-2026-43630.