Test whether an AI agent reveals another user's data or performs actions beyond the caller's permissions. Dialogue probes cover access across users or organizations, admin functions, and attempts to gain higher privileges without authorization.
- Checking access to other users' or organizations' data
- Testing permission checks on admin-only actions
- Checking whether dialogue claims grant higher privileges
Tencent/AI-Infra-Guard☆ 6.9KUpdated Oct 20, 2026
Identify and exploit Broken Object Level Authorization (BOLA), historically known as Insecure Direct Object Reference (IDOR), in API architectures. Extremely common and critical flaw where an API fails to validate whether the currently authenticated user actually owns or retains permissions over the specifically requested database resource (ID).
The English summary is being prepared. Showing the original description.
ShulkwiSEC/bb-huge☆ 23Updated Jul 11, 2026