Microsoft AI Red Team

Microsoft AI Red Team's June 4, 2026 update to its "Taxonomy of Failure Modes in Agentic AI Systems" (v2.0) reports that zero-click attack chains can bypass human-in-the-loop (HitL) approvals end-to-e…

Microsoft updated its operational taxonomy of failure modes for agentic AI systems after 12 months of red teaming, adding seven newly emphasized failure modes including supply-chain compromise and goa…