6 Domains, 60 Tasks, Red+Blue Dual Stack
One suite, covering both the attack side and the defense side
RED TEAM · Attack
BLUE TEAM · Defense
WorkBuddy Bench Security
60 tasks · 6 domains
Whitebox source audit
Real CVEs · find-vuln + PoC
Blackbox binary exploitation
Closed-source ELF · network services
Web exploitation
SSRF · JWT · deserialization
14
Malware analysis
PE/Go/.NET reversing + YARA
8
Security operations & detection
SOC triage · detection-rule authoring
6
AI agent security
Injection · chain hijacking · tool confusion
Difficulty distribution: hard tasks dominate, matching real security work
easy
medium
hard
expert