SOURCE-LINKED INTELLIGENCE

Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding the security surface beyond chat-only models. Yet standard evaluations remain single-turn and fail to capture multi-step agent vulnerabilities. We present a systematic black-box framework for risk-aware agent evaluation requiring only basic system descriptions. Our approach introduces: (1) a seven-domain taxonomy mapping observable behaviors to risk categories, (2) fully automated SAGE-RT red teaming producing 120 adversarial scenarios per domain

Read original source ↗ Open in workspace

recordType

paper

region

Global