Description
llama.cpp b8841 before b11865 contains an out-of-bounds write vulnerability in the ggml-rpc RDMA transport rdma_recv() function that allows unauthenticated peers to overflow the rpc-server stack. Attackers advertising RDMA capabilities in the HELLO message can send up to 256 KiB into a 1-byte stack variable in rpc_serve_client(), crashing the server or potentially executing code.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
ggml-org llama.cpp
Default version status: unaffected
b8841 to < b11865affected
pkg:github/ggml-org/llama.cppReferences
- https://github.com/ggml-org/llama.cpp/pull/30399 ↗
- https://github.com/ggml-org/llama.cpp/commit/9a0fde9967fa1a35b6e5dd1f47e1a3648b6fecc1 ↗
- https://github.com/ggml-org/llama.cpp/blob/620d2225cc436ab0b001e3200e590e3b286ef9ab/ggml/src/ggml-rpc/transport.cpp#L510-L528 ↗
- https://github.com/ggml-org/llama.cpp/releases/tag/b11865 ↗
- https://github.com/ggml-org/llama.cpp ↗
- https://www.vulncheck.com/advisories/llama-cpp-b8841-before-b11865-stack-based-buffer-overflow-via-ggml-rpc-rdma-rdma-recv ↗