Vulnerability 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.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789
- https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9
- https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e
- 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-i
FAQ
What is CVE-2024-58400?
CVE-2024-58400 is a vulnerability with a CVSS score of 8.2 (HIGH). 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 unvalida...
How severe is CVE-2024-58400?
CVE-2024-58400 has been rated HIGH with a CVSS base score of 8.2/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2024-58400?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.