llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
Impact
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.
Source excerpt · VulnCheckAffected packages
Affected products
Vendor version evidence. Product records are separate from automatic dependency matching.
ggml-org · llama.cpp
Other versions: unaffected
| Version / range | Source status |
|---|---|
| b1046 to before b2731 | affected |
Original source 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.
References
- Source reference github.com/ggml-org/llama.cpp/issues/6774
- Patch github.com/ggml-org/llama.cpp/pull/6885
- Patch github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d
- Source reference github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp
- Release notes github.com/ggml-org/llama.cpp/releases/tag/b2731
- Security advisory www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets