securityHigh
341 Malicious OpenClaw Skills Discovered Distributing macOS Malware
Security researchers uncovered a major supply-chain attack in the ClawHub skill marketplace, with 341 malicious skills using typosquatting to distribute malware.
OpenClaw Security Alerts
Security advisories, vulnerability disclosures, and safety alerts. Stay informed to protect yourself.
All Security Alerts
securityMedium
Researchers Find 506 Prompt Injection Attacks Hidden in Moltbook Posts
Independent security researchers identified 506 posts (2.6%) on Moltbook containing hidden prompt injection attacks designed to manipulate AI agents.
securityCritical
Critical Moltbook Database Vulnerability Exposed 1.5 Million Agent API Keys
A critical security vulnerability in Moltbook's Supabase database allowed anyone to access API keys and take control of any AI agent on the platform.
securityHigh
Malicious Chrome Extensions Caught Stealing AI Conversations from 900,000 Users
Security researchers discovered two Chrome extensions impersonating AI tools that were stealing conversations from ChatGPT and DeepSeek sessions.