Sign up to save your podcasts
Or
Share Ep 50 | Niki Aimable Niyikiza - Capability-Based Authorization for AI Agents | [un]prompted 2026
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
![[un]prompted Security Practitioner Con 2026](https://podcast-api-images.s3.amazonaws.com/corona/show/7188602/logo_300x300.jpeg){kind=logo}
Ep 50 | Niki Aimable Niyikiza - Capability-Based Authorization for AI Agents | [un]prompted 2026
Day 2 | Stage 2
Senior Security Engineer & AI Security Researcher from Snap addresses how prompt injection filters and coarse IAM roles consistently fail in multi-agent setups. Shows working alternative: treating agent authority as ephemeral, cryptographic warrants that attenuate on delegation (inspired by Macaroons/UCAN). Task-scoped, holder-bound, verified offline by tools in microseconds. Even fully compromised agent can't escalate or exfiltrate beyond bounds. Includes live demos and benchmarks.
Niki Aimable Niyikiza is Senior Security Engineer & AI Security Researcher, Snap.
Watch on YouTube: https://www.youtube.com/watch?v=bw928cFShK4
View all episodes
By [un]promptedDay 2 | Stage 2
Senior Security Engineer & AI Security Researcher from Snap addresses how prompt injection filters and coarse IAM roles consistently fail in multi-agent setups. Shows working alternative: treating agent authority as ephemeral, cryptographic warrants that attenuate on delegation (inspired by Macaroons/UCAN). Task-scoped, holder-bound, verified offline by tools in microseconds. Even fully compromised agent can't escalate or exfiltrate beyond bounds. Includes live demos and benchmarks.
Niki Aimable Niyikiza is Senior Security Engineer & AI Security Researcher, Snap.
Watch on YouTube: https://www.youtube.com/watch?v=bw928cFShK4