CVE-2024-58399
llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
ggml-org llama.cpp
CVSS
6.9MediumExploitationNo 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 b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights.
Text from CVE List
Affected versions 1
- llama.cppaffected: b1046 before b2731CVE List
References 6
- github.com/ggml-org/llama.cpp/pull/6885Fixvia CVE List
- github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1dFixvia CVE List
- github.com/ggml-org/llama.cpp/releases/tag/b2731Fixvia CVE List
- vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsetsAdvisoryvia CVE List
- github.com/ggml-org/llama.cpp/issues/6774Referencevia CVE List
- github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004Referencevia CVE List