llama.cpp b10398 before b11301 contains an integer overflow vulnerability in gguf_init_from_reader that allows attackers to bypass tensor element-count validation by supplying shapes whose product wraps to zero. Attackers can craft GGUF files with enormous tensor extents that overflow ggml_nbytes() and strides, causing out-of-bounds memory access when buffers are sized from wrapped byte counts.
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
Low
Partial 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/v0.5.0/ggml/src/gguf.cpp#L701
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/commit/2149c00f4442dc59302e134a02e4c99d5f…
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/issues/29383
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/pull/29384
disclosure@vulncheck.com
https://github.com/ggml-org/llama.cpp/releases/tag/b11301
disclosure@vulncheck.com
https://www.vulncheck.com/advisories/llama-cpp-b10398-before-b11301-integer-ove…
disclosure@vulncheck.com