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.
Attack Parameters
Attack Vector
Local
Requires local access
Attack Complexity
Low
Easy to exploit
Attack Requirements
None
No additional conditions
Privileges Required
None
No privileges needed
User Interaction
Passive
Minimal interaction
Impact Assessment
Confidentiality
Low
Partial data leak
Integrity
None
No data modification
Availability
High
Complete denial of service
CVSS Vector v4.0
Weakness Type (CWE)
References 6
https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a…
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/issues/6774
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/pull/6885
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/releases/tag/b2731
disclosure@vulncheck.com
https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-…
disclosure@vulncheck.com