Out-of-bounds Read

Overview Affected versions of this package are vulnerable to Out-of-bounds Read in the GGUF model loader. An attacker can access sensitive server memory contents, including environment variables, API keys, system prompts, and concurrent users' conversation data, by submitting a specially crafted...

Out-of-bounds Read

Overview Affected versions of this package are vulnerable to Out-of-bounds Read in the GGUF model loader. An attacker can access sensitive server memory contents, including environment variables, API keys, system prompts, and concurrent users' conversation data, by submitting a specially crafted...

CVE-2026-7482 Ollama heap out-of-bounds read in GGUF tensor parsing leaks server process memory to unauthenticated remote attackers

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and...

CVE-2026-7482

Ollama CVE-2026-7482 is a heap out-of-bounds read in the GGUF model loader affecting the /api/create path, where an attacker-supplied GGUF file can declare tensor offsets/sizes that exceed the file, causing reads past the allocated heap in fs/ggml/gguf.go and server/quantization.go (WriteTo()). L...

CVE-2026-33298

Summary (CVE-2026-33298) : llama.cpp (C/C++) contains an integer overflow in the ggml_nbytes function during GGUF tensor parsing, allowing an attacker to bypass memory validation by crafting tensor dimensions. This can cause ggml_nbytes to report a far too small size (examples cite 4 MB vs exabyt...

CVE-2026-33298 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

CVE-2026-33298 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

CVE-2026-33298 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

Integer Overflow → Heap Buffer Overflow in BYTES-Tensor Parsing (DoS)

This report is not public...

llama.cpp GGUF library header.n_tensors heap-based buffer overflow vulnerability

Talos Vulnerability Report TALOS-2024-1915 llama.cpp GGUF library header.ntensors heap-based buffer overflow vulnerability February 26, 2024 CVE Number CVE-2024-21836 SUMMARY A heap-based buffer overflow vulnerability exists in the GGUF library header.ntensors functionality of llama.cpp Commit...

Stack overflow

TensorFlow is an open source platform for machine learning. If a list of quantized tensors is assigned to an attribute, the pywrap code fails to parse the tensor and returns a nullptr, which is not caught. An example can be seen in tf.compat.v1.extractvolumepatches by passing in quantized tensors...