325 matches found
Ollama < 0.17.1 - Information Disclosure
Ollama 0.17.1 contains a heap out-of-bounds read caused by improper validation of tensor offset and size in GGUF model loader, letting remote attackers leak sensitive memory data via /api/create and /api/push endpoints, exploit requires no authentication. id: CVE-2026-7482 info: name: Ollama 0.17...
EUVD-2026-128233
llama.cpp MTMD Multimodal GGUF File Parsing Integer Overflow Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of llama.cpp. User interaction is required to exploit this vulnerability in that the target must open a...
EUVD-2026-128232
llama.cpp GGUF File Parsing Heap-based Buffer Overflow Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of llama.cpp. User interaction is required to exploit this vulnerability in that the target must visit a...
EUVD-2026-128231
llama.cpp GGUF File Parsing Integer Overflow Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of llama.cpp. User interaction is required to exploit this vulnerability in that the target must visit a malicious page ...
Malicious code in gguf-accelerator (PyPI)
Source: kam193 ea28ec2703fb6f7c5d2d3bd1afb13431865aa07a2f3ab3728d39f97a33f21751 During installation package downloads and starts a malicious executable identified as likely a coinminer. --- Category: MALICIOUS - The campaign has clearly malicious intent, like infostealers. Campaign:...
CVE-2026-126976
The llama.cpp library is vulnerable to an integer overflow during the parsing of audio multimodal projector GGUF files . The root cause is the lack of proper validation of user-supplied data before buffer allocation, which can lead to Remote Code Execution (RCE) in the context of the current proc...
CVE-2026-126975
The llama.cpp software is vulnerable to a heap-based buffer overflow during the parsing of GGUF files . The root cause is a lack of proper validation on the length of user-supplied data before it is copied into a heap-based buffer. This flaw allows a remote attacker to execute arbitrary code in t...
CVE-2026-126974
The llama.cpp software contains a Remote Code Execution vulnerability (ZDI-CAN-34553) originating from improper validation of user-supplied data during GGUF file parsing . The flaw results in an integer overflow before data is written to memory, potentially allowing an attacker to execute arbitra...
llm-forensics
LLM Forensics Weight-level forensics for causal language models. Point it at two models and it tells you how they are related — and what one of them was taught. Question| Analysis ---|--- How much, and where, did a fine-tune move the weights?| Weight Diff Which tokens do the heaviest updates...
CVE-2026-7482-PoC
CVE-2026-7482: Ollama Heap Out-of-Bounds Read 1-Day PoC This repository contains a 1-day Proof of Concept PoC exploitation chain for CVE-2026-7482 , an unauthenticated Out-of-Bounds OOB Read vulnerability in Ollama's GGUF model loader versions prior to 0.17.1. Note: This is a 1-day research...
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,...
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...
Linux Distros Unpatched Vulnerability : CVE-2026-116816
The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llmtokenizerplamo2::build that allows attackers to corrupt heap memory via...
Linux Distros Unpatched Vulnerability : CVE-2024-58399
The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - 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...
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...
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...
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...