Join the Cyber Forum: Threat Intel on May 12, 2026 to learn how AI is reshaping threat defense.Join the Virtual Cyber Forum: Threat IntelRegister Now
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-2025-6208

CVE-2025-6208: llama_index.core DoS Vulnerability

CVE-2025-6208 is a denial of service vulnerability in llama_index.core caused by uncontrolled memory consumption in SimpleDirectoryReader. This post explains its impact, affected versions, and mitigation steps.

Published: February 6, 2026

CVE-2025-6208 Overview

A resource exhaustion vulnerability has been identified in the SimpleDirectoryReader component of llama_index.core version 0.12.23. The vulnerability arises from a resource management flaw where the user-specified file limit (num_files_limit) is applied only after all files in a directory have been loaded into memory. This improper sequencing allows for uncontrolled memory consumption, potentially leading to memory exhaustion and degraded system performance, particularly in resource-constrained environments.

Critical Impact

Applications using the vulnerable SimpleDirectoryReader component to process directories with large numbers of files may experience memory exhaustion and denial of service conditions, as the file limit parameter fails to prevent initial memory consumption.

Affected Products

  • llama_index.core version 0.12.23
  • LlamaIndex versions prior to 0.12.41

Discovery Timeline

  • 2026-02-02 - CVE CVE-2025-6208 published to NVD
  • 2026-02-03 - Last updated in NVD database

Technical Details for CVE-2025-6208

Vulnerability Analysis

This vulnerability is classified under CWE-400 (Uncontrolled Resource Consumption). The core issue lies in the implementation logic of the SimpleDirectoryReader component, which is designed to read files from a specified directory for document processing in LlamaIndex applications.

The num_files_limit parameter was intended to allow developers to control how many files are processed from a directory. However, the implementation flaw causes all files to be loaded into memory first, with the limit only being applied afterward during filtering. This design deficiency means that even when a developer explicitly sets a low file limit, the component will still consume memory proportional to the total number of files in the directory.

In environments where LlamaIndex is deployed to process directories containing thousands of files, this vulnerability can be exploited to cause denial of service conditions through memory exhaustion.

Root Cause

The root cause is an improper order of operations in the SimpleDirectoryReader component. Instead of checking the num_files_limit parameter before loading files into memory, the implementation loads all directory contents first and then applies the limit filter. This represents a classic resource management flaw where defensive limits are checked too late in the processing pipeline to be effective.

Attack Vector

The attack vector is network-based, requiring no user interaction or special privileges. An attacker could exploit this vulnerability by:

  1. Providing a path to a directory containing an extremely large number of files
  2. Triggering the SimpleDirectoryReader to process this directory
  3. Causing the application to exhaust available memory before the num_files_limit parameter takes effect

The vulnerability can be exploited in any deployment where user input influences the directory path processed by SimpleDirectoryReader, or where the component is used against directories with unexpectedly large file counts.

The fix implemented in version 0.12.41 modifies the file loading logic to apply the num_files_limit constraint before loading files into memory, preventing the resource exhaustion condition. For technical details on the specific code changes, refer to the GitHub commit.

Detection Methods for CVE-2025-6208

Indicators of Compromise

  • Abnormal memory consumption spikes in applications using LlamaIndex SimpleDirectoryReader
  • Application crashes or out-of-memory errors during directory processing operations
  • Slow system performance or unresponsiveness when loading documents from directories
  • Log entries indicating memory allocation failures in LlamaIndex components

Detection Strategies

  • Monitor memory utilization patterns for applications using LlamaIndex document processing
  • Implement application-level logging to track directory operations and file counts processed by SimpleDirectoryReader
  • Set up alerts for sudden memory consumption increases in LlamaIndex-based services
  • Review application dependencies to identify installations of llama_index.core version 0.12.23 or earlier

Monitoring Recommendations

  • Deploy memory usage monitoring with threshold-based alerting for LlamaIndex application processes
  • Implement resource limits (cgroups, container limits) to contain memory exhaustion impacts
  • Monitor system-level metrics including available memory and swap usage on hosts running affected applications
  • Set up dependency scanning to identify vulnerable LlamaIndex versions across your environment

How to Mitigate CVE-2025-6208

Immediate Actions Required

  • Upgrade llama_index.core to version 0.12.41 or later where this vulnerability is resolved
  • Audit all applications using SimpleDirectoryReader to identify potential exposure
  • Implement input validation to restrict directory paths to trusted locations with known file counts
  • Deploy resource limits at the container or process level to prevent memory exhaustion from affecting other services

Patch Information

The vulnerability is fixed in LlamaIndex version 0.12.41. The patch modifies the SimpleDirectoryReader component to apply the num_files_limit parameter before loading files into memory, ensuring that resource constraints are enforced early in the processing pipeline.

The fix can be reviewed in the GitHub commit. Additional details about the vulnerability discovery are available in the Huntr bug bounty report.

Workarounds

  • Pre-filter directories to contain only the required number of files before passing to SimpleDirectoryReader
  • Implement application-level memory limits to prevent complete system exhaustion
  • Use alternative document loading approaches that process files iteratively rather than loading all into memory
  • Deploy the application in containerized environments with strict memory constraints to limit blast radius
bash
# Upgrade LlamaIndex to patched version
pip install --upgrade llama-index-core>=0.12.41

# Verify installed version
pip show llama-index-core | grep Version

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

  • Vulnerability Details
  • TypeDOS

  • Vendor/TechLlama Index

  • SeverityMEDIUM

  • CVSS Score5.3

  • EPSS Probability0.04%

  • Known ExploitedNo
  • CVSS Vector
  • CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
  • Impact Assessment
  • ConfidentialityLow
  • IntegrityNone
  • AvailabilityLow
  • CWE References
  • CWE-400
  • Technical References
  • GitHub Commit Change

  • Huntr Bug Bounty Report
  • Related CVEs
  • CVE-2024-58339: LlamaIndex VannaPack DoS Vulnerability

  • CVE-2024-14021: LlamaIndex Unsafe Deserialization Vulnerability

  • CVE-2024-3098: llama_index safe_eval RCE Vulnerability
Default Legacy - Prefooter | Experience the World’s Most Advanced Cybersecurity Platform

Experience the World’s Most Advanced Cybersecurity Platform

See how our intelligent, autonomous cybersecurity platform can protect your organization now 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