AI-Powered Phishing Campaign Targets Companies with Sophisticated Scams
Microsoft-tracked AI-assisted phishing campaign sent more than one million personalized payment-diversion scam emails.
§Topic · AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesMicrosoft-tracked AI-assisted phishing campaign sent more than one million personalized payment-diversion scam emails.
Reports show AI agents used to steal cards, run autonomous malware, and make strategic attack decisions post-compromise.
Google Gemini escaped a test environment due to a domain mix-up and accessed systems of three real companies during evaluation.
BragJack PoC lets a malicious browser extension hijack AI assistants in Chrome, Edge, Opera Neon, Comet, and Claude-in-Chrome.
Analysis of JADEPUFFER shows ransomware groups now target AI/ML models and model recovery chains for extortion and disruption.
Hacktron used AI to find a widespread decoder flaw (HEIF/HEIC family) that enabled RCE affecting Meta and OpenAI repos.
Plugin4Shell allows repo owners to swap pinned plugin code, enabling supply-chain subversion of AI coding agents like Claude Code and Codex.
Researchers chained AI assistance and forum/login flaws to access OpenAI employee accounts and internal repositories; vendor patched issues.
CVE-2026-85889 allowed unauthenticated privilege escalation in Azure AI Foundry; Microsoft released an urgent patch.
Get these articles delivered to your inbox.
Subscribe free