A Leader in the 2026 Gartner® Magic Quadrant™ for Endpoint Protection. Six years running.Six years. Gartner® Magic Quadrant™ Leader.Find Out Why
Experiencing a Breach?Blog
Get StartedContact Us
SentinelOne
  • Platform
    Platform Overview
    • Singularity Platform
      Welcome to Integrated Enterprise Security
    • AI for Security
      Leading the Way in AI-Powered Security Solutions
    • Securing AI
      Accelerate AI Adoption with Secure AI Tools, Apps, and Agents.
    • How It Works
      The Singularity XDR Difference
    • Singularity Marketplace
      One-Click Integrations to Unlock the Power of XDR
    • Pricing & Packaging
      Comparisons and Guidance at a Glance
    Data & AI
    • Purple AI
      Accelerate SecOps with Generative AI
    • Singularity Hyperautomation
      Easily Automate Security Processes
    • AI-SIEM
      The AI SIEM for the Autonomous SOC
    • AI Data Pipelines
      Security Data Pipeline for AI SIEM and Data Optimization
    • Singularity Data Lake
      AI-Powered, Unified Data Lake
    • Singularity Data Lake for Log Analytics
      Seamlessly Ingest Data from On-Prem, Cloud or Hybrid Environments
    Endpoint Security
    • Singularity Endpoint
      Autonomous Prevention, Detection, and Response
    • Singularity XDR
      Native & Open Protection, Detection, and Response
    • Singularity RemoteOps Forensics
      Orchestrate Forensics at Scale
    • Singularity Threat Intelligence
      Comprehensive Adversary Intelligence
    • Singularity Vulnerability Management
      Application & OS Vulnerability Management
    • Singularity Identity
      Identity Threat Detection and Response
    Cloud Security
    • Singularity Cloud Security
      Block Attacks with an AI-Powered CNAPP
    • Singularity Cloud Native Security
      Secure Cloud and Development Resources
    • Singularity Cloud Workload Security
      Real-Time Cloud Workload Protection Platform
    • Singularity Cloud Data Security
      AI-Powered Threat Detection for Cloud Storage
    • Singularity Cloud Security Posture Management
      Detect and Remediate Cloud Misconfigurations
    Securing AI
    • Prompt Security
      Secure AI Tools Across Your Enterprise
  • Why SentinelOne?
    Why SentinelOne?
    • Why SentinelOne?
      Cybersecurity Built for What’s Next
    • Our Customers
      Trusted by the World’s Leading Enterprises
    • Industry Recognition
      Tested and Proven by the Experts
    • About Us
      The Industry Leader in Autonomous Cybersecurity
    Compare SentinelOne
    • Arctic Wolf
    • Broadcom
    • CrowdStrike
    • Cybereason
    • Microsoft
    • Palo Alto Networks
    • Sophos
    • Splunk
    • Trellix
    • Trend Micro
    • Wiz
    Verticals
    • Energy
    • Federal Government
    • Finance
    • Healthcare
    • Higher Education
    • K-12 Education
    • Manufacturing
    • Retail
    • State and Local Government
  • Services
    Managed Services
    • Managed Services Overview
      Wayfinder Threat Detection & Response
    • Threat Hunting
      World-Class Expertise and Threat Intelligence
    • Managed Detection & Response
      24/7/365 Expert MDR Across Your Entire Environment
    • Incident Readiness & Response
      DFIR, Breach Readiness, & Compromise Assessments
    Support, Deployment, & Health
    • Technical Account Management
      Customer Success with Personalized Service
    • SentinelOne GO
      Guided Onboarding & Deployment Advisory
    • SentinelOne University
      Live and On-Demand Training
    • Services Overview
      Comprehensive Solutions for Seamless Security Operations
    • SentinelOne Community
      Community Login
  • Partners
    Our Network
    • MSSP Partners
      Succeed Faster with SentinelOne
    • Singularity Marketplace
      Extend the Power of S1 Technology
    • Cyber Risk Partners
      Enlist Pro Response and Advisory Teams
    • Technology Alliances
      Integrated, Enterprise-Scale Solutions
    • SentinelOne for AWS
      Hosted in AWS Regions Around the World
    • Channel Partners
      Deliver the Right Solutions, Together
    • SentinelOne for Google Cloud
      Unified, Autonomous Security Giving Defenders the Advantage at Global Scale
    • Partner Locator
      Your Go-to Source for Our Top Partners in Your Region
    Partner Portal→
  • Resources
    Resource Center
    • Case Studies
    • Data Sheets
    • eBooks
    • Reports
    • Videos
    • Webinars
    • Whitepapers
    • Events
    View All Resources→
    Blog
    • Feature Spotlight
    • For CISO/CIO
    • From the Front Lines
    • Identity
    • Cloud
    • macOS
    • SentinelOne Blog
    Blog→
    Tech Resources
    • SentinelLABS
    • Ransomware Anthology
    • Cybersecurity 101
  • About
    About SentinelOne
    • About SentinelOne
      The Industry Leader in Cybersecurity
    • Investor Relations
      Financial Information & Events
    • SentinelLABS
      Threat Research for the Modern Threat Hunter
    • Careers
      The Latest Job Opportunities
    • Press & News
      Company Announcements
    • Cybersecurity Blog
      The Latest Cybersecurity Threats, News, & More
    • FAQ
      Get Answers to Our Most Frequently Asked Questions
    • DataSet
      The Live Data Platform
    • S Foundation
      Securing a Safer Future for All
    • S Ventures
      Investing in the Next Generation of Security, Data and AI
  • Pricing
Get StartedContact Us
CVE Vulnerability Database
Vulnerability Database/CVE-2024-39721

CVE-2024-39721: Ollama Ollama DOS Vulnerability Explained

CVE-2024-39721 is a denial of service vulnerability in Ollama Ollama that causes infinite goroutine blocking through user-controlled file paths. This article covers technical details, affected versions, impact, and mitigation.

Published: June 2, 2026

CVE-2024-39721 Overview

CVE-2024-39721 is a denial-of-service vulnerability in Ollama versions before 0.1.34. The flaw resides in the CreateModelHandler function in server/routes.go, which uses os.Open to read a user-controlled file path until completion. An unauthenticated remote attacker can submit a request with req.Path set to a blocking device file such as /dev/random, causing the handling goroutine to run indefinitely. The goroutine continues consuming resources even after the client aborts the HTTP request. Repeated requests exhaust available goroutines and memory, degrading or halting the Ollama service. The issue is tracked under [CWE-404: Improper Resource Shutdown or Release].

Critical Impact

Unauthenticated attackers can remotely exhaust server resources on Ollama instances, taking the AI model serving endpoint offline without requiring credentials or user interaction.

Affected Products

  • Ollama versions prior to 0.1.34
  • Self-hosted Ollama deployments exposing the HTTP API
  • Containerized Ollama instances using vulnerable base images

Discovery Timeline

  • 2024-10-31 - CVE-2024-39721 published to NVD
  • 2025-05-13 - Last updated in NVD database

Technical Details for CVE-2024-39721

Vulnerability Analysis

Ollama is an open-source runtime for serving large language models over an HTTP API. The CreateModelHandler accepts a JSON request that includes a Path field pointing to a model file on disk. The handler calls os.Open against this attacker-supplied path and reads the file until end-of-file is reached. Reads from character devices like /dev/random block when insufficient entropy is available, producing data slowly or indefinitely. Because Go uses a goroutine per request, the blocked read does not release the worker.

Go's HTTP server does not cancel goroutines when a client disconnects unless the handler explicitly checks the request context. The vulnerable code path lacks such cancellation, so aborted requests still hold open file descriptors and stack memory. An attacker scripting repeated POST requests to the create-model endpoint can rapidly accumulate stuck goroutines and trigger denial of service.

Root Cause

The root cause is improper validation and lifecycle management of a user-controlled file path. The handler trusts req.Path without restricting it to regular files, model directories, or whitelisted locations. The code also fails to bound read durations or honor request cancellation signals from the HTTP context.

Attack Vector

Exploitation requires network access to the Ollama API endpoint. The attacker sends a crafted JSON payload to the model creation route with Path pointing at /dev/random, /dev/zero, a FIFO, or another blocking source. No authentication or user interaction is required when the API is exposed. Repeated requests amplify the impact until the host runs out of usable goroutines or memory. Technical references include the vulnerable code in routes.go and the Oligo Security analysis.

Detection Methods for CVE-2024-39721

Indicators of Compromise

  • HTTP POST requests to /api/create containing a path field referencing /dev/random, /dev/urandom, /dev/zero, or named pipes
  • Sustained growth in Ollama process goroutine count, file descriptors, or resident memory
  • API response timeouts and unresponsive model creation endpoints
  • Multiple concurrent long-lived connections from a single source to the Ollama HTTP port (default 11434)

Detection Strategies

  • Inspect web proxy and application logs for path parameters referencing device files or non-standard locations outside the configured models directory
  • Correlate aborted client connections with persistent server-side resource consumption tied to the Ollama process
  • Alert on Ollama processes whose goroutine or file descriptor counts exceed baseline thresholds

Monitoring Recommendations

  • Capture HTTP request bodies for the Ollama API and parse them for suspicious path values
  • Track per-source request rates against /api/create and rate-limit anomalous spikes
  • Forward Ollama process metrics, network telemetry, and host logs to a centralized analytics platform for cross-source correlation

How to Mitigate CVE-2024-39721

Immediate Actions Required

  • Upgrade Ollama to version 0.1.34 or later on every host running the service
  • Remove direct internet exposure of the Ollama API and place it behind an authenticated reverse proxy
  • Audit existing deployments and container images to confirm the patched version is in use
  • Restrict the operating system account running Ollama so it cannot read sensitive device files

Patch Information

The maintainers addressed CVE-2024-39721 in Ollama 0.1.34. The fix tightens handling in CreateModelHandler so that user-controlled paths no longer cause indefinite blocking reads. Review the updated routes.go for the corrected behavior and pull the latest container image or binary release from the official Ollama repository.

Workarounds

  • Place Ollama behind a reverse proxy that enforces authentication and rejects requests whose path field references device files or paths outside an allow-listed model directory
  • Apply network-level access controls so only trusted internal hosts can reach the Ollama API port
  • Run Ollama inside a container or sandbox that does not expose /dev/random, /dev/urandom, or other blocking devices to the process
  • Configure request timeouts and connection limits at the proxy layer to bound resource consumption per client
bash
# Example reverse proxy hardening (nginx)
location /api/create {
    limit_req zone=ollama_create burst=5 nodelay;
    client_body_timeout 10s;
    proxy_read_timeout 30s;
    proxy_pass http://127.0.0.1:11434;
}

Disclaimer: This content was generated using AI. While we strive for accuracy, please verify critical information with official sources.

  • Vulnerability Details
  • TypeDOS

  • Vendor/TechOllama

  • SeverityHIGH

  • CVSS Score7.5

  • EPSS Probability0.21%

  • Known ExploitedNo
  • CVSS Vector
  • CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
  • Impact Assessment
  • ConfidentialityLow
  • IntegrityNone
  • AvailabilityHigh
  • CWE References
  • CWE-404
  • Technical References
  • GitHub Code Fragment

  • GitHub Code Fragment

  • Oligo Security Blog Post
  • Related CVEs
  • CVE-2025-66960: Ollama DoS Vulnerability in GGUF Parser

  • CVE-2025-66959: Ollama GGUF Decoder DoS Vulnerability

  • CVE-2025-15514: Ollama Null Pointer Dereference DoS Flaw

  • CVE-2025-1975: Ollama Server DoS Vulnerability
Default Legacy - Prefooter | Experience the World’s Most Advanced Cybersecurity Platform

Experience the Most Advanced Cybersecurity Platform

See how the world’s most intelligent, autonomous cybersecurity platform can protect your organization today and into the future.

Try SentinelOne
  • Get Started
  • Get a Demo
  • Product Tour
  • Why SentinelOne
  • Pricing & Packaging
  • FAQ
  • Contact
  • Contact Us
  • Customer Support
  • SentinelOne Status
  • Language
  • Platform
  • Singularity Platform
  • Singularity Endpoint
  • Singularity Cloud
  • Singularity AI-SIEM
  • Singularity Identity
  • Singularity Marketplace
  • Purple AI
  • Services
  • Wayfinder TDR
  • SentinelOne GO
  • Technical Account Management
  • Support Services
  • Verticals
  • Energy
  • Federal Government
  • Finance
  • Healthcare
  • Higher Education
  • K-12 Education
  • Manufacturing
  • Retail
  • State and Local Government
  • Cybersecurity for SMB
  • Resources
  • Blog
  • Labs
  • Case Studies
  • Videos
  • Product Tours
  • Events
  • Cybersecurity 101
  • eBooks
  • Webinars
  • Whitepapers
  • Press
  • News
  • Ransomware Anthology
  • Company
  • About Us
  • Our Customers
  • Careers
  • Partners
  • Legal & Compliance
  • Security & Compliance
  • Investor Relations
  • S Foundation
  • S Ventures

©2026 SentinelOne, All Rights Reserved.

Privacy Notice Terms of Use

English