Menu

Star on GitHub · 3.4k

CVE-2026-103663

Ollama is vulnerable to path traversal in the `/api/pull` endpoint due to insufficient validation of layer digests by the `digestToPath` function.

Published Oct 8, 2026CWE-23EPSS 0.71%

Overview

CVE-2026-103663 is a known-severity vulnerability. It was published on October 8, 2026.

Technical description

Ollama is vulnerable to path traversal in the `/api/pull` endpoint due to insufficient validation of layer digests by the `digestToPath` function. An unauthenticated remote attacker can specify a path traversal sequence as a layer digest, causing a malicious binary to be written outside the model store. 

Critically if the server process has write access to `/usr/lib/ollama` (the default in most Ollama Docker images), an attacker can write the malicious file to that directory. On the next server restart, the file is loaded and executed, resulting in remote code execution as root.

This issue was fixed in version 0.35.0.

Remediation

Check the references section for vendor advisories, patches, and mitigation guidance. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

Frequently asked questions

What is CVE-2026-103663?

CVE-2026-103663 is a known-severity vulnerability. It was published on October 8, 2026.

How severe is CVE-2026-103663?

CVSS score information is not yet available for this vulnerability. Check back as the CVE record is updated by NVD analysts.

How do I fix or remediate CVE-2026-103663?

Check the references section for vendor advisories, patches, and mitigation guidance. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

How can CyberStrike help with CVE-2026-103663?

CyberStrike is an open-source, AI-augmented pentesting engine. Rather than flag a version number, it tests whether an issue like CVE-2026-103663 is actually reachable in your own applications and APIs, then verifies each finding before reporting it. That tells you if the weakness is a real, exploitable risk in your environment or a false positive you can safely deprioritize.

CyberStrike v2 is here — more intelligence, greater reach