Phishing emails are now baiting your AI assistant, not you
Apollo_R · hn · 2026-10-13
Malwarebytes warns that attackers are now designing phishing emails targeted at AI assistants rather than humans.
- Email content is crafted to make AI assistants that read mail take actions: clicking links, leaking info, executing tasks
- Automated mail handling creates a new attack surface invisible to the human recipient
- A prompt-injection-style threat vector that's actively spreading in the wild
More from Safety
- Crime group used Claude, Grok and Kimi agents to attack 400+ banks in Latin America — anshulkundaje · 2026-10-23
- Greg Brockman: AI makes hacking 100x more profitable and easier, upending hacker economics — gabriel1 · 2026-10-23
- Account hacks surge: 6-step emergency checklist plus an AI audit prompt — petergyang · 2026-10-23
- For consumer AI founders, 'When are you launching in Europe?' is the new 'When Android?'—only 100x worse — omooretweets · 2026-10-23
- mmitchell_ai questions whether the AI safety vs security framing stems from EA — mmitchell_ai · 2026-10-23
- MPI-Sec PhD Thesis on Vulnerability Detection Benchmarks Includes Pre-LLM Classic "Top Score on the Wrong Exam" — mboehme_ · 2026-10-23