Mehdi Akiki

Posts tagged "authorization"

  • Published on
    Roll out one narrow internal assistant before adding write actions. Read-only still requires authorization, output limits, and checks against private-data exposure.
  • Published on

    Article · Through the layers

    Put two tenants in your authorization tests

    A one-tenant fixture cannot show cross-tenant access bugs. Exercise reads, writes, and reused database connections with two independent customer scopes.
  • Published on
    An indirect prompt injection becomes an application-security incident when model output carries authority into tools. Limit capabilities, track provenance, and enforce policy outside the model.
  • Published on
    A reference flow for keeping user identity, tenant, audience, and allowed actions attached to every AI tool call without trusting the model to enforce permissions.