Capability-Based Authorization for AI Agents

Niki Aimable Niyikiza, Senior Security Engineer & AI Security Researcher, Snap, speaks at [un]prompted 2026 on: Capability-Based Authorization for AI Agents: Warrants That Survive Prompt Injection. Prompt injection filters and coarse IAM roles cons...

Niki Aimable Niyikiza, Senior Security Engineer & AI Security Researcher, Snap, speaks at [un]prompted 2026 on: Capability-Based Authorization for AI Agents: Warrants That Survive Prompt Injection.

Prompt injection filters and coarse IAM roles consistently fail in multi-agent setups.
I'll show a working alternative: treating agent authority as ephemeral, cryptographic warrants that attenuate on delegation (inspired by Macaroons/UCAN), task-scoped, holder-bound, and verified offline by tools in microseconds. Even a fully compromised agent can't escalate or exfiltrate beyond its bounds.
Live demos in LangChain/LangGraph multi-agent workflows, benchmarks against adaptive injection/escalation attacks, and an honest look at remaining gaps (e.g., constraints that require runtime context).
Audience Takeaways:
1) Why identity-based authorization fails for AI agents.
2) How capability tokens bound blast radius without blocking legitimate use.
3) Practical patterns for delegation in multi-agent systems.