Launching today
Blacksmith Guard

Blacksmith Guard

Benchmark the safety of autonomous offensive AI agents

1 follower

Test whether autonomous offensive AI agents operate safely. Blacksmith Guard uses 48 adversarial scenarios and 12 safety properties to evaluate scope enforcement, data protection, collateral impact, resource usage, and human control.
Blacksmith Guard gallery image
Free
Launch Team
Render Sandboxes: a computer for every agent
Render Sandboxes: a computer for every agentRun untrusted code safely. Idle sandboxes cost nothing
Promoted