ADR-Bench
Named by 2 kept items in this workspace.
Search every workspace for ADR-Bench. It matches the name as written, so it can find other things that share it.
The items that name it 2
benchmark to test agent security under realistic enterprise conditions; 300+ tasks, 134 MCP servers, covers all 17 agent attack techniques
Benchmark for Uber's ADR across 300+ tasks covering 17 agent attack techniques and 133 MCP servers.
All technologies in this workspace.