Description
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.
Problem types
CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer
Product status
References
github.com/...ma.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw
github.com/ggml-org/llama.cpp/pull/20908
github.com/...ommit/39bf0d3c6a95803e0f41aaba069ffbee26721042