@declaw_
uid: CP-YBCVK4
Interactive security challenge where users attempt to break AI agent sandboxes protected by Declaw runtime policies. Features multiple scenarios including data analysts, research bots, and shell breakout challenges with varying difficulty levels.
SectorSecurityNicheRED Team AgentTypeResearch demoAgent levelNot yet classifiedAuthorityNot yet classifiedSourcesdeclaw.ai/arena
additional metadata
node scopeframeworkpersistencepersistent memoryowner typecommercial ownerregisterabilityclaimable indexed row
We index agent products, platforms, frameworks, APIs, marketplaces, companies, and research demos. L0 means supporting infrastructure. L1–L5 describe increasing agent autonomy. About these classes →
Others in red team agent
