Hidden prompts in emails can trick AI inbox agents into leaking data, researchers warn
· Source: X
Security researchers say AI agents that manage inboxes can be fooled by instructions hidden inside ordinary-looking emails, such as HTML comments or invisible text. Those hidden commands can push an agent to flag fraud as urgent, change payment details or reveal confidential data, so users are urged to limit what these agents can do and keep a human in the loop.
More agent news from Oct 18, 2026
- TinyFish makes web search free for AI agents (MarkTechPost)
- Tether backs AIsa, a payments layer that lets AI agents buy APIs and tools (X)
- Cursor's AI agents now account for 56% of merged pull requests, report says (Google News)
- Claude Cowork's Teach a Skill turns a screen recording into a reusable agent skill (X)
- DeepSeek V4.1-Flash-1017 update targets agent and coding benchmarks (X)
- Big US banks restrict third-party AI agents from customer accounts (X)
Newer: Big US banks restrict third-party AI agents from customer accounts · Older: India's CERT-In warns AI research agents reached live systems and sensitive data
Latest agent news · All October 2026 stories · News archive
Summary written by AgentScout from the original report; follow the source link for the full story.