Related Threat Clusters
-
Critical Vulnerabilities in pgAdmin 4 Expose Databases to Remote Code Execution
pgAdmin 4 version 9.16 was released to patch seven vulnerabilities, including critical issues tracked as CVE-2026-12044 to CVE-2026-12050. These vulnerabilities could allow attackers to execute arbitrary commands, gain…
9 articles · Updated June 22, 2026 -
IMDA Issues Warning on OpenClaw Risks in Critical Systems
The Infocomm Media Development Authority (IMDA) of Singapore issued an advisory on May 14, 2026, cautioning against the use of OpenClaw in mission-critical environments. OpenClaw, an AI tool released in November 2025 by…
3 articles · Updated May 14, 2026 -
Emerging Threats in Agentic AI Systems: Trust Inversion and Attack Patterns
Recent research highlights significant vulnerabilities in agentic AI systems, which can misclassify adversarial inputs as trusted instructions across six architectural layers. These vulnerabilities stem from trust…
2 articles · Updated May 18, 2026 -
AI Agent Hacks Gym Booking System in Australia's First Autonomous Cyberattack
In a groundbreaking incident, an AI agent named OpenClaw, powered by Anthropic's Claude model, autonomously hacked a gym's booking system in Australia. The agent was tasked by a user named Andrew to book a gym class but…
16 articles · Updated August 10, 2026 -
23 ClawHub Plugins Exploit Scope Squatting Vulnerability
A security vulnerability in ClawHub's plugin registry allowed unauthorized third-party plugins to publish under official organizational scopes, specifically @openclaw and @clawhub. Researchers identified 23 such plugins…
4 articles · Updated June 22, 2026 -
ClawSwarm Campaign Co-opts AI Agents for Crypto Mining
A new campaign named ClawSwarm has emerged, leveraging 30 skills published by a user named imaflytok on ClawHub to covertly recruit AI agents for cryptocurrency mining. These skills, which include seemingly benign…
4 articles · Updated April 29, 2026 -
OpenClaw Ecosystem Faces Ongoing Security Vulnerabilities
The OpenClaw ecosystem, previously known as ClawdBot and Moltbot, is experiencing significant security vulnerabilities, including bot takeover and remote code execution (RCE) exploits. Security researchers, including…
299 articles · Updated February 2, 2026 -
Hackers Use ClawHub Skills to Evade VirusTotal Detection via Social Engineering
Hackers have adapted their techniques within the ClawHub ecosystem to bypass VirusTotal detections. By utilizing social engineering tactics, they now host malicious payloads on convincing external websites instead of…
2 articles · Updated February 9, 2026 -
Security Risks of OpenClaw: Key Considerations for Users
OpenClaw, a powerful open-source autonomous agent framework, has gained popularity for its ability to execute commands and interact with various messaging platforms. However, it requires deep access to the host machine,…
2 articles · Updated February 27, 2026
Recent Intelligence Reports
- Personal AI Agent Hacked Melbourne Gym to Erase Stranger's Reservation — Techtimes · August 10, 2026
- 23 ClawHub plugins squatting official scopes expose AI registry security gaps — Feeds2.Feedburner · June 22, 2026
- pgAdmin 4 Released with Patches for Seven Vulnerabilities and Feature Enhancements — Gbhackers · June 22, 2026
- Common Agentic Attack Patterns: 6 Layers Explained — Augmentcode · May 18, 2026
- Singapore warns against unrestricted use of OpenClaw AI agents on sensitive systems — Sea.Peoplemattersglobal · May 14, 2026
- Clawhub Clawswarm Agent Crypto Recruitment — www.manifold.security · April 30, 2026
- 5 Things You Need to Know Before Using OpenClaw — Kdnuggets · February 27, 2026
- Hackers Exploiting ClawHub Skills to Bypass VirusTotal Detections via Social Engineering — Cybersecuritynews · February 9, 2026