At [un]prompted 2026, TrendAI™ demonstrated how documents can be used to exploit AI-driven KYC pipelines. Principal Threat Researcher Sean Park discussed 'When Passports Execute: Exploiting AI-Driven KYC Pipelines.' He showed that these pipelines are actually execution environments, allowing hidden 'injects' in a document to trick an AI agent into reading and writing data across different customer records. In another session titled FENRIR: AI Hunting for AI Zero Days at Scale, Threat Hunting Senior Manager Peter Girnus and Threat Researcher Demeng Chen introduced the automated system that processes large codebases with multiple tools to uncover weaknesses in the AI ecosystem.
TrendAI™ at [un]prompted 2026: From KYC Exploits to Agentic Defense
Summary: TrendAI™ demonstrated at [un]prompted 2026 how AI-driven KYC pipelines can be exploited and introduced FENRIR, an automated system for discovering AI vulnerabilities.
Key facts
- Documents can be exploited in AI-driven KYC pipelines.
- FENRIR is an automated system for discovering vulnerabilities in AI systems at scale.
Why it matters
The findings from this event highlight the growing attack surface of AI systems and emphasize the need for proactive defense mechanisms, such as FENRIR, to secure these environments against potential vulnerabilities.
@trendaisecurity
Embedded content for: TrendAI™ at [un]prompted 2026: From KYC Exploits to Agentic Defense