CVE-2024-58400
llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
ggml-org llama.cpp
CVSS
8.8HighExploitationNo known exploitationNot in CISA KEV, which does not prove it is unexploitedCISA KEV
Exploit odds (EPSS)No scoreNo FIRST EPSS score in this snapshot yet
Fixed inNone listedNo source names a fixed version. Check the vendor advisory below
What fixes it
No source in this snapshot names a fixed version. The vendor advisories under References are the place to check.
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.
Text from CVE List
Affected versions 1
- llama.cppaffected: all versions before b3701CVE List
References 6
- github.com/ggml-org/llama.cpp/pull/9359Fixvia CVE List
- github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3Fixvia CVE List
- github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327feFixvia CVE List
- github.com/ggml-org/llama.cpp/releases/tag/b3701Fixvia CVE List
- vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-idsAdvisoryvia CVE List
- github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789Referencevia CVE List