Skip to content
OpenAdvisories
Medium WID-SEC-2026-2105 1 CVE

Ollama (Quantization Engine): Schwachstelle ermöglicht Offenlegung von Informationen

Published Jun 28, 2026 · Updated Jun 28, 2026 · de-DE

Summary

Ein entfernter, anonymer Angreifer kann eine Schwachstelle in Ollama ausnutzen, um Informationen offenzulegen.

Product

Ollama ist eine Open-Source-Runtime zum lokalen Ausführen von Large Language Models (LLMs)

Vulnerabilities 1

  • High 7.5

    There exists an unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine

    Unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine allows an attacker to read and exfiltrate the server's heap memory, potentially leading to sensitive data exposure, further compromise, and stealthy persistence.

Revision history

  1. #1

    Initiale Fassung

References