← all datasets

Agent Security Bench (ASB)

Emerging
2papers using it
2026first seen

The Agent Security Bench (ASB) is a dataset/benchmark used to evaluate the security of tool-using large language model (LLM) agents against unauthorized actions and the exposure of sensitive plaintext during runtime.

🔎 Find this dataset

Papers using Agent Security Bench (ASB) (2)

Agent Security Bench (ASB) — datasets — ai-agents