Security advisory for llama.cpp

Advisory overview

llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to the llama-server /completion endpoint with IDs outside 0 to n_vocab to read embedding memory out of bounds or crash the process.

Related references

• https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789
• https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe
• https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3
• https://github.com/ggml-org/llama.cpp/pull/9359
• https://github.com/ggml-org/llama.cpp/releases/tag/b3701
• https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids