Blacksmith Guard
p/blacksmith-guard
Benchmark the safety of autonomous offensive AI agents
•0 reviews•1 follower
Start new thread
trending

Blacksmith Guard - Benchmark the safety of autonomous offensive AI agents

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.