The SentinelOne Annual Threat Report - A Defenders Guide from the FrontlinesThe SentinelOne Annual Threat ReportGet the Report
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-2026-45001

CVE-2026-45001: Openclaw Auth Bypass Vulnerability

CVE-2026-45001 is an authentication bypass vulnerability in Openclaw that allows unauthorized access to operator-trusted settings via gateway endpoints. This article covers the technical details, affected versions, and mitigation.

Published: May 18, 2026

CVE-2026-45001 Overview

CVE-2026-45001 is a missing authorization vulnerability [CWE-862] in OpenClaw versions prior to 2026.4.20. The flaw resides in the agent-facing gateway endpoints config.patch and config.apply, which fail to protect operator-trusted settings from mutation by agent tooling. Protected settings include sandbox policy, plugin enablement, gateway authentication and TLS, hook routing, Model Context Protocol (MCP) server configuration, Server-Side Request Forgery (SSRF) policy, and filesystem hardening. A prompt-injected model with access to the owner-only gateway tool can persist unauthorized changes to these protected operator settings, undermining the security boundary between the agent and its host configuration.

Critical Impact

Prompt injection against an OpenClaw agent with gateway tool access can silently rewrite sandbox, SSRF, TLS, and MCP configuration, enabling persistent downgrade of host-level guardrails.

Affected Products

  • OpenClaw (Node.js distribution) versions prior to 2026.4.20
  • Deployments exposing the agent-facing gateway config.patch endpoint
  • Deployments exposing the agent-facing gateway config.apply endpoint

Discovery Timeline

  • 2026-05-11 - CVE-2026-45001 published to the National Vulnerability Database (NVD)
  • 2026-05-13 - Last updated in NVD database

Technical Details for CVE-2026-45001

Vulnerability Analysis

OpenClaw exposes a gateway tool that lets an operator-controlled model adjust runtime configuration through the config.patch and config.apply endpoints. These endpoints accept arbitrary configuration keys without enforcing a server-side allowlist that separates agent-mutable settings from operator-only settings. As a result, the trust boundary between the language model and the host operator collapses at the configuration layer.

An attacker who can influence model input — for example through indirect prompt injection in retrieved documents or tool outputs — can instruct the model to invoke the gateway tool against protected keys. The mutation is persisted, so the weakened policy survives session resets and continues to apply to future agent operations.

The affected protected surfaces include sandbox enforcement flags, plugin enablement, gateway authentication and TLS settings, hook routing, MCP server registration, SSRF egress policy, and filesystem hardening flags. Each of these controls is foundational to containing the agent, so disabling them sets up follow-on impact such as outbound SSRF, malicious MCP server attachment, or sandbox escape.

Root Cause

The gateway mutation guard does not differentiate between operator-trusted configuration keys and agent-permitted keys. Because authorization is missing on protected paths, any caller of the gateway tool inherits operator-level write capability over the configuration.

Attack Vector

Exploitation is network-reachable and requires that the targeted agent have access to the owner-only gateway tool. The attacker delivers prompt-injection content the model will ingest, causing the model to issue config.patch or config.apply calls against protected settings.

typescript
// Source: https://github.com/openclaw/openclaw/commit/fe30b31a97a917ecc6e92f6c85378b6b20352422
// Patch: src/security/dangerous-config-flags.ts
 import { resolveAgentWorkspaceDir, resolveDefaultAgentId } from "../agents/agent-scope.js";
+import { DANGEROUS_SANDBOX_DOCKER_BOOLEAN_KEYS } from "../agents/sandbox/config.js";
 import type { OpenClawConfig } from "../config/types.openclaw.js";
 import {
   collectPluginConfigContractMatches,

The patch imports DANGEROUS_SANDBOX_DOCKER_BOOLEAN_KEYS into the dangerous-config-flags module and tightens the gateway mutation guard so protected keys cannot be written through the agent-facing endpoints.

Detection Methods for CVE-2026-45001

Indicators of Compromise

  • Gateway audit log entries showing config.patch or config.apply calls that target sandbox, TLS, auth, MCP, SSRF, or filesystem keys.
  • Unexpected newly registered MCP servers or hook routes appearing in the OpenClaw configuration store.
  • Sandbox or SSRF policy flags transitioning from a restrictive to a permissive state outside of a change window.
  • Agent transcripts containing instructions to invoke the gateway tool against operator-only settings.

Detection Strategies

  • Compare the persisted OpenClaw configuration against a known-good baseline and alert on drift in protected keys.
  • Parse gateway request logs for config.patch and config.apply calls whose key paths intersect the operator-trusted set.
  • Correlate prompt-injection signals in retrieved content with subsequent gateway tool invocations from the same agent session.

Monitoring Recommendations

  • Forward OpenClaw gateway and agent logs into a centralized analytics pipeline for retention and search.
  • Track the OpenClaw version in use across hosts and flag any instance below 2026.4.20.
  • Monitor outbound network behavior for SSRF or MCP server connections that would only succeed if egress policy was relaxed.

How to Mitigate CVE-2026-45001

Immediate Actions Required

  • Upgrade OpenClaw to version 2026.4.20 or later, which contains the tightened gateway mutation guard.
  • Audit current configuration for unauthorized changes to sandbox, TLS, auth, MCP, SSRF, hook, plugin, and filesystem settings, and restore baseline values.
  • Rotate any gateway authentication credentials or TLS material that may have been altered while the guard was weak.
  • Restrict network exposure of the agent-facing gateway to trusted operator networks only.

Patch Information

The fix is delivered in commit fe30b31 and documented in the GitHub Security Advisory GHSA-7jm2-g593-4qrc. Additional context is available in the VulnCheck Advisory on OpenClaw.

Workarounds

  • Revoke agent access to the owner-only gateway tool until the upgrade is applied.
  • Place the gateway behind a reverse proxy that rejects config.patch and config.apply calls referencing protected key prefixes.
  • Run OpenClaw with a read-only configuration mount so persisted mutations cannot survive a restart.
bash
# Verify the installed OpenClaw version meets the fixed release
npm list openclaw

# Upgrade to the patched release
npm install openclaw@>=2026.4.20

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

  • Vulnerability Details
  • TypeAuth Bypass

  • Vendor/TechOpenclaw

  • SeverityMEDIUM

  • CVSS Score6.0

  • EPSS Probability0.03%

  • Known ExploitedNo
  • CVSS Vector
  • CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
  • Impact Assessment
  • ConfidentialityLow
  • IntegrityNone
  • AvailabilityNone
  • CWE References
  • CWE-862
  • Technical References
  • GitHub Security Advisory GHSA-7jm2
  • Vendor Resources
  • GitHub Commit Details

  • VulnCheck Advisory on OpenClaw
  • Related CVEs
  • CVE-2026-8305: Openclaw Authentication Bypass Vulnerability

  • CVE-2026-45006: Openclaw Auth Bypass Vulnerability

  • CVE-2026-45005: Openclaw Auth Bypass Vulnerability

  • CVE-2026-45002: Openclaw Auth Bypass 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