# 175,000 Exposed Ollama Hosts Enabling LLM Abuse

> 175,000+ Ollama AI inference servers are exposed to the internet without authentication, creating the largest known mass-exploitable AI infrastructure surface in history. Ollama — the most popular open-source project for running AI models (162K+ GitHub stars, hundreds of thousands of monthly Docker Hub pulls) — has NO built-in authentication. Its default Docker deployment binds to 0.0.0.0:11434, exposing the full API to the internet. Automated scanning by criminal groups discovers these instances via Shodan/Censys port 11434 enumeration, enabling: (1) LLMjacking — compute theft at $46K-$100K+/day per compromised cloud account via AWS Bedrock/Anthropic API abuse, (2) Model theft — downloading proprietary fine-tuned models via /api/pull, (3) Remote code execution — CVE-2024-37032 (Probllama) path traversal → ld.so.preload hijack → root RCE on Docker instances, (4) GPU cryptomining pivot — repurposing GPU-rich LLM hosts for cryptocurrency mining, (5) Data exfiltration — accessing training data and conversation logs stored on exposed instances. This is the MongoDB/Elasticsearch exposure pattern (2017-2020) repeating in the AI era: massively deployed infrastructure with no authentication by default, discoverable via internet scanning, and exploited at scale within months. The economics are orders of magnitude worse: MongoDB ransom demanded $1,000; LLMjacking generates $46K/DAY. Wiz Research discovered 1,000+ instances with exposed private models in their initial scan. Sysdig TRT documented OAI Reverse Proxy monetization infrastructure selling stolen LLM access. The scanning → exploitation pipeline is fully automated: port 11434 scan → /api/tags to enumerate models → /api/generate for compute theft → /api/pull for model theft → Probllama RCE for persistent access.

- **Published:** 2026-02-02T20:40:00Z
- **Last reviewed:** 2026-02-02T20:40:00Z
- **Canonical:** https://intel.threadlinqs.com/threat/TL-2026-0020
- **Card image:** https://intel.threadlinqs.com/og/threat/threat-intel-ollama-exposure-llmjacking-tl-2026-0020.webp?v=63cf0c76 (Threadlinqs threat intel: Ollama 175,000 Unauthenticated Hosts: Detection & IOCs (TL-2026-0020) — Medium severity, 49 IOCs, 16 detection rules.)
- **ID:** TL-2026-0020
- **Severity:** MEDIUM (CVSS 6.5)
- **Category:** MISCONFIGURATION
- **Status:** ACTIVE
- **Detections:** 16 (1 shown free below) · **IOCs:** 49
- **CVEs:** CVE-2024-37032

## Description

Ollama is a platform that simplifies running large language models locally, inspired by Docker's container model for AI. With 162K+ GitHub stars and widespread adoption in development, research, and production AI pipelines, it has become the de facto standard for self-hosted LLM inference. The critical security problem: Ollama has NO built-in authentication mechanism. The API server exposes endpoints that provide full control over the instance — model management, inference, file operations — to anyone who can reach port 11434.

The mass exposure problem is architectural:

1. DEFAULT DOCKER BINDING: Ollama's Docker image (ollama/ollama) binds to 0.0.0.0:11434 by default. Every Docker deployment without explicit network configuration exposes the API to all interfaces. Docker's default networking maps container ports to 0.0.0.0 on the host, meaning a simple 'docker run -p 11434:11434 ollama/ollama' exposes the instance to the entire internet if the host has a public IP.

2. NO AUTHENTICATION: Ollama provides zero authentication capability. There is no username/password, no API key, no token system, no OAuth. The project recommends deploying behind a reverse proxy with authentication — but this is not the default and most users don't configure it. Ollama's own GitHub issues (#849) document the feature request for built-in auth, which remains unimplemented.

3. SCANNING DISCOVERY: Criminal groups use Shodan, Censys, and custom scanners to enumerate port 11434 across the internet. A simple Shodan query 'port:11434' returns 175,000+ results. Each result is a fully accessible Ollama instance. The scanning → exploitation pipeline is automated: enumerate hosts → check /api/tags for available models → assess GPU capability → monetize via compute theft or model theft.

4. API ABUSE SURFACE: Exposed Ollama APIs enable complete control:
   - /api/generate — Run inference on any available model (compute theft)
   - /api/chat — Interactive chat sessions consuming GPU compute
   - /api/pull — Download models from the instance (model theft)
   - /api/push — Push models to external registries
   - /api/delete — Delete models (denial of service/data destruction)
   - /api/create — Create custom models from Modelfiles
   - /api/tags — Enumerate all available models (reconnaissance)
   - /api/show — Show model details including parameters and license

5. CVE-2024-37032 (PROBLLAMA): Discovered by Wiz Research, this path traversal vulnerability in Ollama's /api/pull endpoint allows arbitrary file write on the server. In Docker deployments (which run as root), exploitation chain: malicious manifest → path traversal in digest field → write to /etc/ld.so.preload → shared library loaded on next process creation → root RCE. Patched in Ollama 0.1.34 but many exposed instances remain unpatched.

Comparison to MongoDB/Elasticsearch mass exposure (2017-2020):
- MongoDB (2017): ~68,000 exposed instances → ransom attacks → $1,000 demands
- Elasticsearch (2019): ~36,000 exposed instances → data theft → identity fraud
- Ollama (2024-2026): 175,000+ exposed instances → compute theft → $46K-$100K+/DAY

The pattern is identical: popular infrastructure software with no authentication by default, deployed by developers who don't configure network security, discovered via internet scanning, and exploited at scale. But the economics are fundamentally different: database ransom was a one-time $1K demand per instance; LLMjacking generates $46K/day in ongoing compute theft per compromised cloud account. The financial incentive for attackers is 1,000-100,000x higher.

Sysdig TRT documented the OAI Reverse Proxy ecosystem: stolen LLM access is monetized via reverse proxy infrastructure that sells access to multiple compromised accounts. Users pay for access; attackers manage pools of stolen credentials. Prices: $30 for 30-day access tokens. The proxy checks if logging is enabled and refuses to use credentials with CloudTrail logging — OPSEC-aware criminal infrastructure.

Geographic distribution: exposed Ollama instances span AWS, GCP, Azure, DigitalOcean, Hetzner, OVH, and on-premises networks. Cloud deployments are highest risk because the underlying cloud accounts have IAM roles that may provide access to additional cloud services (Bedrock, Vertex AI, SageMaker). Compromising an Ollama instance on a cloud VM is often the entry point to broader cloud account compromise.

## MITRE ATT&CK

- T1190 Exploit Public-Facing Application
- T1583.004 Server
- T1496 Resource Hijacking
- T1595 Active Scanning
- T1596 Search Open Technical Databases
- T1078 Valid Accounts
- T1203 Exploitation for Client Execution
- T1059 Command and Scripting Interpreter
- T1574 Hijack Execution Flow
- T1068 Exploitation for Privilege Escalation
- T1685 Disable or Modify Tools
- T1528 Steal Application Access Token
- T1580 Cloud Infrastructure Discovery
- T1046 Network Service Discovery
- T1213 Data from Information Repositories
- T1567 Exfiltration Over Web Service
- T1485 Data Destruction
- T1657 Financial Theft
- T1583 Acquire Infrastructure
- T1133 External Remote Services
- T1036 Masquerading
- T1552 Unsecured Credentials
- T1210 Exploitation of Remote Services
- T1136 Create Account
- T1530 Data from Cloud Storage
- T1489 Service Stop
- T1590 Gather Victim Network Information
- T1588 Obtain Capabilities
- T1082 System Information Discovery
- T1611 Escape to Host

## Free detection (Splunk SPL, Microsoft KQL)

**External Ollama API Access** (`TL-2026-0020-DET-001`)

Detects external IP addresses accessing Ollama API endpoints

- **Languages:** Splunk SPL, Microsoft KQL
- **Data sources:** firewall, proxy, netflow
- **Severity:** high
- **Confidence:** high

### Splunk SPL

```spl
index=network sourcetype=firewall OR sourcetype=netflow
| where dest_port=11434
| where NOT cidrmatch("10.0.0.0/8", src_ip) AND NOT cidrmatch("172.16.0.0/12", src_ip) AND NOT cidrmatch("192.168.0.0/16", src_ip)
| stats count dc(src_ip) as unique_sources values(src_ip) as external_ips by dest_ip
| where count > 0
| eval alert_severity="HIGH"
| eval alert_reason="Ollama API accessed from external IP - check for unauthorized exposure"
| table dest_ip, count, unique_sources, external_ips, alert_severity, alert_reason
```

### Microsoft KQL

```kql
// External Ollama API Access
// Detects external IP addresses accessing Ollama API endpoints
DeviceNetworkEvents
| where Timestamp > ago(24h)
| where ActionType == "ConnectionSuccess"
// Add destination filters based on threat IOCs
| project Timestamp, DeviceName, RemoteIP, RemotePort, RemoteUrl, InitiatingProcessFileName
| summarize ConnectionCount=count(), Ports=make_set(RemotePort) by DeviceName, RemoteIP
| where ConnectionCount > 5
```

**Known false positives:**

- Intentionally exposed Ollama instances with proper access controls

**Tuning notes:** Whitelist known authorized external sources if applicable

### 15 more detection rules (Splunk SPL, Microsoft KQL, Sigma), unlock with TL Creds

- Ollama Model Pull from Unknown Source (locked: unlock with TL Creds)
- Unusual Ollama Process Resource Consumption (locked: unlock with TL Creds)
- Internet-Exposed Ollama Discovery (locked: unlock with TL Creds)
- Ollama Probllama RCE — ld.so.preload Modification and Shared Library Injection (locked: unlock with TL Creds)
- Ollama Docker Container Running as Root with Internet-Exposed Port Binding (locked: unlock with TL Creds)
- Ollama API Data Destruction — /api/delete from External Source (locked: unlock with TL Creds)
- Ollama API External Inference Request — Unauthenticated Compute Theft (locked: unlock with TL Creds)
- CVE-2024-37032 Probllama — ld.so.preload Modification on Linux Host (locked: unlock with TL Creds)
- Ollama /api/pull from External Registry — Malicious Model Supply Chain and Probllama Vector (locked: unlock with TL Creds)
- Ollama API External Access — Unauthenticated Compute Theft via /api/generate (locked: unlock with TL Creds)
- Ollama Model Enumeration and Theft Pipeline — /api/tags Recon Followed by /api/pull Exfiltration (locked: unlock with TL Creds)
- Ollama Port 11434 Internet Exposure — Firewall/Security Group Misconfiguration Compliance (locked: unlock with TL Creds)
- Ollama API Port 11434 Internet Exposure — Unauthorized External Access (locked: unlock with TL Creds)
- Ollama ld.so.preload Modification — CVE-2024-37032 Probllama RCE Indicator (locked: unlock with TL Creds)
- Ollama API Unauthorized Access from External Network — Compute Theft or Model Theft (locked: unlock with TL Creds)

Sign up free to unlock the detection rules: https://threadlinqs.com/?modal=signup

## Sources

- [Wiz Research — Probllama: Ollama RCE (CVE-2024-37032)](https://www.wiz.io/blog/probllama-ollama-vulnerability-cve-2024-37032)
- [Sysdig TRT — LLMjacking: Stolen Cloud Credentials](https://sysdig.com/blog/llmjacking-stolen-cloud-credentials-used-in-new-ai-attack/)
- [Ollama GitHub Repository](https://github.com/ollama/ollama)
- [Ollama Docker Hub](https://hub.docker.com/r/ollama/ollama)
- [Ollama API Documentation](https://github.com/ollama/ollama/blob/main/docs/api.md)
- [NVD — CVE-2024-37032](https://nvd.nist.gov/vuln/detail/CVE-2024-37032)
- [OAI Reverse Proxy Source](https://gitgud.io/khanon/oai-reverse-proxy)
- [Kingbased/keychecker — LLM Credential Validator](https://github.com/kingbased/keychecker)
- [AWS Bedrock Pricing](https://aws.amazon.com/bedrock/pricing/)
- [Wiz — State of AI in the Cloud 2024](https://www.wiz.io/blog/key-findings-from-the-state-of-ai-in-the-cloud-report-2024)
- [Oligo Security — ShadowRay (Ray Anyscale)](https://www.oligo.security/blog/shadowray-attack-ai-workloads-actively-exploited-in-the-wild)
- [Wiz — Hugging Face AI Infrastructure Risks](https://www.wiz.io/blog/wiz-and-hugging-face-address-risks-to-ai-infrastructure)
- [Wiz — Replicate AI Vulnerability](https://www.wiz.io/blog/wiz-research-discovers-critical-vulnerability-in-replicate)
- [Shodan — Port 11434 Search](https://www.shodan.io/search?query=port%3A11434)
- [Ollama GitHub Issue #849 — Auth Request](https://github.com/ollama/ollama/issues/849)

## Full data

The other 15 detection rules (Splunk SPL / Microsoft KQL / Sigma) unlock with TL Creds; a free account includes daily creds: https://threadlinqs.com/?modal=signup
Indicator values unlock with TL Creds, at a lower price on Red and Purple; AI agents can query rules and IOCs through the Threadlinqs MCP server (Purple): https://intel.threadlinqs.com/mcp

Canonical: https://intel.threadlinqs.com/threat/TL-2026-0020
