Skip to content
Forest Global Training Partners
Home Services AI Governance AI Risk Encyclopedia Contact Us
AI Risk Encyclopedia AI Use CasesAI RisksAI Hallucinations Topics Entities Sources
  1. Home
  2. AI Risks
  3. Notion 3.0's new AI agents can be tricked into leaking…

AI Risks September 22, 2025 · The Decoder

Notion 3.0's new AI agents can be tricked into leaking data through a malicious PDF

It didn't take long for Notion 3.0's new AI agents to show a serious weakness: they can be tricked into leaking sensitive data through something ...

Read the original at The Decoder ↗

Topics
AI Safety & Existential RiskAI Agents & Automation
Tracked via
“dangerous AI”

Related articles

  • AI agents tricked by a rogue downloads file into running dangerous malware - Yahoo Tech AI Risks · Oct 28, 2026
  • Your AI Agents Might Be Leaking Data — Watch this Webinar to Learn How to Stop It AI Risks · Jul 04, 2025
  • ServiceNow AI Agents Can Be Tricked Into Acting Against Each Other via Second-Order Prompts AI Risks · Nov 19, 2025
  • Employees are leaking data over Gen AI tools, here's what enterprises need to do AI Risks · Aug 17, 2024
  • ChatGPT tricked to swipe sensitive data from Gmail - BusinessGhana AI Risks · Sep 22, 2025
  • AI Adoption Is Racing Ahead of Security While Leaking Sensitive Data - WWD AI Risks · Nov 07, 2026

AI Risk Encyclopedia is a curated research index from Forest Global Training Partners. Articles belong to their publishers; we link to and summarize them.

Contact