Detections
Analytics

Ollama Unauthenticated Access

critical Nessus Plugin ID 302134

Synopsis

The remote host is running an AI model runtime that allows unauthenticated access.

Description

Ollama, a local large language model (LLM) runtime, was detected on the remote host via its HTTP API.

By default, Ollama binds only to localhost (127.0.0.1) and does not provide built-in authentication. Detecting it on a network-accessible interface indicates that the configuration has been changed to bind to a non-loopback address (e.g. by setting OLLAMA_HOST=0.0.0.0), exposing the full API to unauthenticated users.

An unauthenticated attacker with network access can:

 - Run arbitrary LLM inference queries, consuming GPU and compute resources

 - List, pull, and delete models

 - Exfiltrate proprietary or fine-tuned model data

 - Use the instance as an anonymous AI proxy

Solution

Bind Ollama to localhost (127.0.0.1) or place it behind a reverse proxy that enforces authentication. Do not expose the Ollama API directly to untrusted networks.

See Also

https://www.ollama.com/

Plugin Details

Severity: Critical

ID: 302134

File Name: ollama_web_detect.nbin

Version: 1.1

Type: remote

Published: 3/13/2026

Updated: 3/13/2026

Asset Inventory: true

Supported Sensors: Nessus

Risk Information

CVSS Score Rationale: Unauthenticated network access to the full ollama api allows complete compromise of the service including model exfiltration, deletion, and resource abuse.

CVSS v2

Risk Factor: Critical

Base Score: 10

Vector: CVSS2#AV:N/AC:L/Au:N/C:C/I:C/A:C

CVSS Score Source: manual

CVSS v3

Risk Factor: Critical

Base Score: 10

Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

CVSS v4

Risk Factor: Critical

Base Score: 10

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

Vulnerability Information

CPE: cpe:/a:ollama:ollama

Reference Information

CWE: 284