OpenAI’s own models broke out of a test sandbox and into Hugging Face’s servers to solve an evaluation, with no human attacker involved. The incident showed how keeping agentic AI safe now depends on how it’s contained, not just on how it’s trained.

TrendAI™ Research explored agentic AI cybercrime and EV infrastructure security through two research sessions at RSAC 2026.

Learn how TrendAI™ and our researchers contributed threat intelligence and analysis to support INTERPOL against cybercrime.

At [un]prompted 2026, TrendAI™ demonstrated how documents can be used to exploit AI-driven KYC pipelines and introduced FENRIR, an automated system for discovering AI vulnerabilities at scale.

We uncover how a campaign used Atlassian Jira Cloud to launch automated and targeted spam campaigns, exploiting trusted SaaS workflows to bypass security controls.