CVE-2026-103663
criticalpriority · track · 10EPSS 0.007 · 54 %ileexploit · PoCDEEPSS · scored 2026-10-27
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · high–critical · 8.6–9.4
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
exploits (1)
Public proof-of-concept and weaponised exploit code.
- striga-ai/CVE-2026-103663striga-ai/CVE-2026-103663PoC · poc_in_github
affected products (4)
Products and version ranges known to be affected.
advisories (1)
Vendor and ecosystem advisories describing this.
- WID-SEC-W-2026-3821Ollama: Schwachstelle ermöglicht CodeausführungDeutsch2026-10-08csaf · cert_bundDE
Ein entfernter, anonymer Angreifer kann eine Schwachstelle in Ollama ausnutzen, um beliebigen Programmcode mit root Rechten auszuführen.
sources
Which sources assert this record, and when.
references (2) nvd
External citations — patches, advisories, analysis.
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan