Live › vulnerability › CVE-2024-58399
Go to dashboardllama.cpp versions before b2731 have an out-of-bounds read in llama_model_loader when a GGUF model file contains crafted tensor offsets. A malicious model file can crash the process or load adjacent process memory as model weights.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-27 01:34 UTC. All times on this page are UTC.
Teams that run llama.cpp, or products built on it, and load GGUF model files that they did not create themselves. Systems that only load models from a fixed, trusted set of files are at much lower risk. unknown whether the sources name specific downstream products.
No product ranges from the sources yet.
llama-cli --version or looking at the build metadata, and compare it with b2731.b2731 or later.Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
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.
This page as .md · .json · in your agent: get_signal("CVE-2024-58399")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.