Skip to content
  • Home
  • Cyber Map
  • About Us – Contact
  • Disclaimer
  • Terms and Rules
  • Privacy Policy
Cyber Web Spider Blog – News

Cyber Web Spider Blog – News

Globe Threat Map provides a real-time, interactive 3D visualization of global cyber threats. Monitor DDoS attacks, malware, and hacking attempts with geo-located arcs on a rotating globe. Stay informed with live logs and archive stats.

  • Home
  • Cyber Map
  • Cyber Security News
  • Security Week News
  • The Hacker News
  • How To?
  • Toggle search form
Critical Flaws in OpenClaw Allow AI Agent Hijacking

Critical Flaws in OpenClaw Allow AI Agent Hijacking

Posted on June 4, 2026 By CWS

Five zero-day vulnerabilities have been identified in OpenClaw, allowing attackers to breach trust boundaries and take control of AI agents across various messaging services.

OpenClaw integrates AI agents into platforms like Slack, Discord, Microsoft Teams, Matrix, and Telegram. It uses user-defined allowlists to regulate who can interact with these agents. However, this trust model relies on the assumption that only those specifically approved can issue commands, potentially accessing sensitive data or systems.

Underlying Vulnerabilities

Philip Garabandic discovered that the trust model fails due to improper identity resolution during the allowlist processing. Human-readable identifiers like display names are converted to stable user IDs during service initialization. Since display names can be changed on many platforms, attackers can impersonate trusted users by altering their names to match those on the allowlist.

This issue was first seen in OpenClaw’s Telegram integration and patched following advisory GHSA-mj5r-hh7j-4gxf. Despite this, the root cause persisted in five other extensions, namely Slack, Discord, Matrix, Zalo, and Microsoft Teams, due to similar insecure implementations.

Security Implications

The fundamental vulnerability lies in the flawed startup resolution process. While runtime checks validate stable user IDs, initialization logic uses mutable fields like display names to resolve allowlist entries. If attackers change their display names to match allowlisted users before a service restart, they may gain unauthorized access.

Once successful, attackers can fully control agent interactions, leaving legitimate users excluded. The vulnerabilities were found using agentgg, an AI-driven static analysis tool that generates custom detectors based on historical advisories.

Addressing the Flaws

OpenClaw maintainers have acknowledged and addressed the vulnerabilities, implementing fixes that enforce strict ID-based matching. They also added configuration flags to control name-based resolution.

These vulnerabilities are classified under CWE-639, involving authorization bypass using user-controlled identifiers. The impact is severe in AI environments, where unauthorized access can lead to command execution, data theft, or system infiltration.

Garabandic emphasizes the need for systemic detection mechanisms to prevent such vulnerabilities from spreading across implementations. By leveraging historical data for automated detection, organizations can enhance security and maintain trust in AI-driven infrastructures.

For further insights, attend the upcoming webinar on OWASP API Top 10 and learn strategies to close visibility gaps with WAAP.

Cyber Security News Tags:agentgg, AI agents, AI security, AI-driven analysis, authorization bypass, CWE-639, Cybersecurity, Discord, identity spoofing, Microsoft Teams, OpenClaw, Slack, Telegram, zero-day vulnerabilities

Post navigation

Previous Post: Microsoft Debuts AI Agent Scout for Seamless Integration
Next Post: Bots Dominate Global Web Traffic, Surpassing Humans

Related Posts

Amazon WorkSpaces For Linux Vulnerability Let Attackers extract valid authentication token Amazon WorkSpaces For Linux Vulnerability Let Attackers extract valid authentication token Cyber Security News
Arizona Attorney General Suses Chinese E-commerce Retailer Temu Over Data Theft Claims Arizona Attorney General Suses Chinese E-commerce Retailer Temu Over Data Theft Claims Cyber Security News
Researchers Uncover Hidden Connections Between Ransomware Groups and Relationships Between Them Researchers Uncover Hidden Connections Between Ransomware Groups and Relationships Between Them Cyber Security News
SnappyClient Malware Threatens Windows with Stealthy Data Breaches SnappyClient Malware Threatens Windows with Stealthy Data Breaches Cyber Security News
AI Pentest Tool Enhances Security Testing with New Features AI Pentest Tool Enhances Security Testing with New Features Cyber Security News
20 Best Endpoint Management Tools 20 Best Endpoint Management Tools Cyber Security News

Categories

  • Cyber Security News
  • How To?
  • Security Week News
  • The Hacker News

Recent Posts

  • Bots Dominate Global Web Traffic, Surpassing Humans
  • Critical Flaws in OpenClaw Allow AI Agent Hijacking
  • Microsoft Debuts AI Agent Scout for Seamless Integration
  • Cyberattack Alert on U.S. Automatic Tank Gauge Systems
  • US Firms Under Siege from New JS.MonoGlyphRAT Malware

Pages

  • About Us – Contact
  • Disclaimer
  • Privacy Policy
  • Terms and Rules

Archives

  • June 2026
  • May 2026
  • April 2026
  • March 2026
  • February 2026
  • January 2026
  • December 2025
  • November 2025
  • October 2025
  • September 2025
  • August 2025
  • July 2025
  • June 2025
  • May 2025

Recent Posts

  • Bots Dominate Global Web Traffic, Surpassing Humans
  • Critical Flaws in OpenClaw Allow AI Agent Hijacking
  • Microsoft Debuts AI Agent Scout for Seamless Integration
  • Cyberattack Alert on U.S. Automatic Tank Gauge Systems
  • US Firms Under Siege from New JS.MonoGlyphRAT Malware

Pages

  • About Us – Contact
  • Disclaimer
  • Privacy Policy
  • Terms and Rules

Categories

  • Cyber Security News
  • How To?
  • Security Week News
  • The Hacker News

Copyright © 2026 Cyber Web Spider Blog – News.

Powered by PressBook Masonry Dark