CVEvulnerability
CVE-2024-58400
8.8 HIGH
Official page ↗
- Status
- Awaiting Analysis
- Published
- 2026-10-27
- Last modified
- 2026-10-27
- Assigner
- [email protected]
- CVSS 4.0 ([email protected])
- 8.8 HIGH — CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
- CVSS 3.1 ([email protected])
- 8.2 HIGH — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
- Weaknesses
- CWE-129
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.
Related
Weakness · CWE (1)
- CWE-129 Improper Validation of Array Index weakness
References
- https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789 github.com
- https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe github.com
- https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3 github.com
- https://github.com/ggml-org/llama.cpp/pull/9359 github.com
- https://github.com/ggml-org/llama.cpp/releases/tag/b3701 github.com
- https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids www.vulncheck.com