MemGhost Attack: One Email Plants Persistent False Memories in AI Agents
A new attack named MemGhost demonstrates how a single email can inject persistent false memories into AI personal assistants, manipulating their future…
Tag: OpenClaw
WhatsApp-to-Host Attack Chain Exploits Three OpenClaw Flaws for Code Execution
Security researcher Chinmohan Nayak has detailed a WhatsApp-to-host attack chain leveraging three now-patched vulnerabilities in the OpenClaw personal AI assistant. The flaws,…
Cyera Disclosed Claw Chain Vulnerabilities in May
Cyera previously disclosed the Claw Chain vulnerabilities in OpenClaw, which required prior foothold for exploitation.
HalluSquatting Attack Exploits AI Coding Assistants to Deliver Botnet Malware
Researchers from Tel Aviv University, Technion, and Intuit have identified a novel attack vector called HalluSquatting that exploits AI coding assistants' tendency…
SkillCloak Technique Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing
Researchers at the Hong Kong University of Science and Technology have developed a technique called SkillCloak that allows malicious AI agent skills…
WhatsApp Used as Entry Vector in OpenClaw Attack Chain
WhatsApp messages were used as the initial vector to trigger host code execution via OpenClaw vulnerabilities.
OpenClaw: Open-Source AI Personal Agent
OpenClaw is an open-source AI personal agent that maintains persistent memory in plain text files (AGENTS.md, MEMORY.md). It was the primary target…
OpenClaw Patches Three High-Severity Flaws in AI Assistant
OpenClaw released version 2026.6.6 to fix three vulnerabilities that could allow command injection, path traversal, and sandbox escape.
OpenClaw AI Agent Vulnerable to Code Execution and Data Exfiltration via Hidden Commands and Phishing
Two security teams have demonstrated that OpenClaw, a popular self-hosted AI agent, can be tricked into executing attacker-controlled code or leaking sensitive…