← All posts

Type · 2 pieces

Research on authorization for agentic systems

Long-form research on why identity-based access control breaks down for autonomous agents and what a capability-based model looks like.

Research

We attacked OWASP FinBot with Promptfoo. Tenuo blocked every successful exploit.

We red-teamed OWASP FinBot's AI agents with Promptfoo, with Tenuo on and off. As shipped, 50 attacks got through. With Tenuo, none did.

  • AI agent security
  • Prompt injection
Read research →
Research

Authorization for Agentic Systems

Why identity and role-based access control leave an authorization gap for autonomous agents, and how task-scoped warrants close it across delegation chains.

  • Agentic governance
  • AI agent security
Read research →