{"id":"CVE-2024-58400","aliases":[],"url":"https://o3.security/vulnerability/CVE-2024-58400","summary":"llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs","details":"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.","published":"2026-10-27T00:33:57.354Z","modified":"2026-10-28T02:54:27.672885761Z","cvss":null,"epss":null,"cisaKev":null,"exploitsKnown":null,"affectedPackages":[],"fix":{"url":"https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe","label":"ggml-org/llama.cpp@eae5971"},"references":[{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2024/58xxx/CVE-2024-58400.json"},{"type":"ADVISORY","url":"https://github.com/ggml-org/llama.cpp/releases/tag/b3701"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2024-58400"},{"type":"ADVISORY","url":"https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids"},{"type":"FIX","url":"https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe"},{"type":"FIX","url":"https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3"},{"type":"FIX","url":"https://github.com/ggml-org/llama.cpp/pull/9359"},{"type":"ARTICLE","url":"https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-10-28T02:54:27.672885761Z"}}