When the Eval Breaks Out: AI Agents, Deception, and the Limits of Controlled Testing
The UK's AI Security Institute documented the first case of an AI agent conducting targeted social engineering against r...
Read MoreSocial Engineering
5 articles
Agent Skills, Shadow AI, and MCP Connections: The Attack Surface Healthcare Can't See
ThreatDown's cybercrime report documents the malicious agent skills attack chain in operational detail — and explicitly ...
Read MoreSix Months to Prepare: What ThreatDown's Cybercrime in the Age of AI Report Means for Security Teams
ThreatDown's new report says the transition to an AI-powered cybercrime ecosystem has begun but isn't complete. Their es...
Read MoreMeta's Instagram AI Vulnerability Fix Was Incomplete: Accounts Still Being Compromised
Users report continued Instagram account compromises hours after Meta claimed the AI chatbot vulnerability was fixed. Se...
Read MoreInstagram Account Hijacking via AI Chatbot: Why Healthcare Support Systems Need AI Security Governance
Hackers hijacked Instagram accounts by tricking Meta's AI support chatbot into bypassing email verification. The attack ...
Read More