PT-2026-34454 · Ollama · Ollama
Published
2026-04-22
·
Updated
2026-05-06
·
CVE-2026-5757
None
No severity ratings or metrics are available. When they are, we'll update the corresponding info on the page.
Name of the Vulnerable Software and Affected Versions
Ollama (affected versions not specified)
Description
An out-of-bounds heap read/write issue exists in the GGUF model quantization engine. An attacker can exploit this by uploading a specially crafted GPT-Generated Unified Format (GGUF) file to the model upload interface. Because the quantization engine lacks proper bounds checking and trusts tensor metadata, it can be triggered to read beyond intended memory boundaries, allowing unauthenticated remote exfiltration of sensitive heap memory from the server. This may lead to unauthorized data access, system compromise, and stealthy persistence.
Recommendations
At the moment, there is no information about a newer version that contains a fix for this vulnerability.
Found an issue in the description? Have something to add? Feel free to write us 👾
Related Identifiers
Affected Products
Ollama