{"id":"CVE-2024-58400","published":"2026-10-27T01:19:03.080","lastModified":"2026-10-27T01:19:03.080","description":"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.","cvssScore":8.2,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H","cwes":["CWE-129"],"vendors":[],"products":[],"references":[{"url":"https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/pull/9359","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/releases/tag/b3701","tags":[]},{"url":"https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids","tags":[]}],"exploitRefs":[{"url":"https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/pull/9359","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/releases/tag/b3701","tags":[]}],"hasPoc":true,"ai":null}