CVE-2024-58400
CVE-2024-58400 · llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
This page contains facts from public vulnerability sources. Check the original advisory before updating.
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.
CVSS 8.8 · High · EPSS 0.4%
- Published
- Updated
Stack: system
Affected products and versions
llama.cpp
- Versions
- ≥ 0, < b3701: Affected (custom)
No fix published
llama.cpp Ubuntu:26.10
- Versions
- 8681+dfsg-1
- 9721+dfsg-1ubuntu1
- 10438+dfsg-1
- 10438+dfsg-1ubuntu1
- Affected ranges
- ECOSYSTEM: (−∞, +∞)
No fix published
llama.cpp Ubuntu:26.04:LTS
- Versions
- 5882+dfsg-2
- 8064+dfsg-1ubuntu1
- 8681+dfsg-1
- Affected ranges
- ECOSYSTEM: (−∞, +∞)
No fix published
Original sources
- https://github.com/ggml-org/llama.cpp/pull/9359
- https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3
- https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe
- https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789
- 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
- https://nvd.nist.gov/vuln/detail/CVE-2024-58400