CVE-2026-85180: Ollama 0.30.0 through 0.33.2 SSRF via Cross-Host Tensor Blob Redirect

Published Sep 3, 2026
·
Updated

Ollama fails to validate redirect destinations when pulling tensor-layer models, allowing unauthenticated attackers to redirect blob downloads to arbitrary hosts. An attacker can control a registry, serve a malicious tensor-layer manifest, and cause the server to issue GET requests to internal hosts including cloud metadata endpoints.

Affected Software

1 affected component
Ollama Ollama>=0.30.0<=0.33.2

Event History

Sep 3, 2026
CVE Published
via MITRE·02:12 PM
Data Sourced
via MITRE·02:12 PM
DescriptionSeverityWeakness

Frequently Asked Questions

1

What must an attacker control to exploit this issue?

The attacker must control a model registry and serve a malicious tensor-layer manifest. They can use redirects in blob downloads to make the Ollama server send GET requests to arbitrary hosts.

2

Which systems are most exposed?

Ollama instances that pull tensor-layer models from an attacker-controlled registry are exposed. The impact is especially relevant where the Ollama server can reach internal-only services or cloud metadata endpoints.

3

Does exploitation require authentication or user interaction?

No. The supplied vector indicates network exploitation with low attack complexity, no privileges required, and no user interaction.

4

How can I determine whether an instance is affected?

Check whether the deployed Ollama version is from 0.30.0 through 0.33.2 and whether it pulls tensor-layer models. Review download activity for blob requests redirected to hosts outside the intended registry, particularly internal addresses or cloud metadata endpoints.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203