CVE-2024-42479 llama.cpp allows write-what-where in rpc_server::set_tensor
An attacker can achieve arbitrary memory write and potential code execution via unsafe pointer handling in the RPC server tensor setting function.
- 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-2024-42479?
CVE-2024-42479 is a critical memory corruption vulnerability in ggerganov llama.cpp, published on 12 Aug 2024. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address writing. This vulnerability is fixed in b3561.
Which versions are affected by CVE-2024-42479?
It affects 1 product.
Products include Ggml Llama.cpp.
How do I fix CVE-2024-42479?
No fix has been published for CVE-2024-42479 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-2024-42479 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2024-42479 exists.
Other vulnerabilities in ggerganov llama.cpp
- 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
- CVE-2026-21869 llama.cpp has Out-of-bounds Write in llama-server
Sources
Also known as GHSA-wcr5-566p-9cwj.