Barracuda uncovers phishing emails that target both humans and AI assistants
JamesIvings · x · 2026-11-01
- Barracuda Research reports a new phishing tactic: a single email attacks both the human recipient and the AI assistant processing it.
- Humans face social engineering (e.g. password-protected attachments), while the AI is hit with prompt injections designed to influence or override its behavior.
- A sample email masquerades as internal correspondence: identical sender/recipient addresses, a trusted public-sector domain, and a clean spam confidence score to bypass reputation-based filtering.
- As users rely on AI for summarizing, prioritizing, and acting on email, Barracuda urges organizations to secure not just users and inboxes but also the AI systems that consume email data.
More from Safety
- ResGate cuts agent resource-hijacking attack success from 84.1% to 23.6% — jiqizhixin · 2026-11-01
- Ed Newton-Rex slams OpenAI's robots.txt opt-out as 'fake consent' six years too late — TuhinChakr · 2026-11-01
- Should MCP servers start with zero network? A sandboxed Claude Code setup argues yes — quiet_flare · 2026-11-01
- Anthropic's self-assessment makes Claude flag misuse right after each reply — adamamcbride · 2026-11-01
- How one tap on a notification can land your job-hunt chat in your work ChatGPT account — Ok_Negotiation_2587 · 2026-11-01
- Fake bank chatbot leaked data in 54 of 55 attacks; one gateway cut it to zero — its_vayishu · 2026-11-01