CVE-2026-5757

Name of the Vulnerable Software and Affected Versions Ollama (affected versions not specified)

Description An out-of-bounds memory read and write issue exists in the GGUF (GPT-Generated Unified Format) quantization engine. This occurs because the engine lacks proper bounds checking and trusts tensor metadata, allowing reads beyond intended memory boundaries. An unauthenticated attacker can exploit this by uploading a specially crafted GGUF file, triggering the vulnerability during the quantization process to read and exfiltrate sensitive heap memory from the server. This may lead to unauthorized data access, system compromise, and stealthy persistence. Approximately 300,000 deployments are potentially affected.

Recommendations At the moment, there is no information about a newer version that contains a fix for this vulnerability. Restrict or disable model uploads and limit exposure to trusted environments to minimize the risk of exploitation.