CVE-2026-7482

CVE-2026-7482: Ollama GGUF Heap OOB Read Reproduction This repository contains my local reproduction script for CVE-2026-7482, a heap out-of-bounds read in vulnerable Ollama GGUF loading and quantization paths. The important result from this work is narrow: I was able to make the Heap OOB conditi...

CVE-2026-7482

🚨 CVE-2026-7482: Heap Buffer Over-Read in Ollama 📝 Description CVE-2026-7482 identifies a critical heap buffer over-read vulnerability in the /api/create and /api/push endpoints of Ollama , an open-source framework for running local language models. This vulnerability allows a remote,...

CVE-2026-116816

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llmtokenizerplamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like whose negative parsed value writes token ids before the bytes buffer...

context-segmentation

Context Segmentation for SLM Agents This is the implementation of the solution proposed in the scientific paper: Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks Setup Ensure you have Python 3.12.3+ installed along with Docker engine Python environment python...

DEBIAN-CVE-2026-116816

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llmtokenizerplamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like whose negative parsed value writes token ids before the bytes buffer...

CVE-2026-116816

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llmtokenizerplamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like whose negative parsed value writes token ids before the bytes buffer...

CVE-2024-58399

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader 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...

CVE-2026-116816 llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llmtokenizerplamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like whose negative parsed value writes token ids before the bytes buffer...

CVE-2026-116816 llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llmtokenizerplamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like whose negative parsed value writes token ids before the bytes buffer...

CVE-2026-116816

The software llama.cpp (versions b5899 before b10261 ) is affected by a heap out-of-bounds write vulnerability within the llm_tokenizer_plamo2::build function. The root cause is the improper validation of array indices when processing crafted GGUF models ; specifically, attackers can provide BYTE...

EUVD-2026-110569

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llmtokenizerplamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like whose negative parsed value writes token ids before the bytes buffer...

CVE-2024-58399 llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader 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...

CVE-2024-58399

The llama.cpp library (versions prior to b2731 ) contains an out-of-bounds read vulnerability within the llama_model_loader component. An attacker can exploit this by providing a crafted or truncated GGUF model file containing arbitrary 64-bit tensor offsets. This allows the attacker to read memo...

CVE-2024-58399 llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader 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...

EUVD-2024-55826

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader 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...

PT-2026-125540

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 t...

PT-2026-125545

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm tokenizer plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like whose negative parsed value writes token ids before the bytes buffer...

PT-2026-125546

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...

PT-2026-125551

llama.cpp b5854 before b11275 contains an integer overflow vulnerability in gguf init from reader that bypasses the CVE-2025-53630 size check when padding near-SIZE MAX tensor sizes. Attackers can supply a crafted GGUF file whose tensor size pads to zero, causing an undersized data blob and...

UBUNTU-CVE-2024-58399

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader 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...