ConsultingWorkbench-backed AI security engagements — map, attack, defend, and prove your AI systems.
Scope a Review
AI Product Security Assessment — Labs

Hands-On AI Security Labs

Scenario-based lab tracks across red team, blue team, RAG security, agentic workflows, governance evidence, and product security. Earn domain badges by completing track scenarios.

Browse Labs Open Trust Scanner

Lab Tracks

rose track

Red Team Track

Adversarial offensive scenarios for AI systems.

blue track

Blue Team Track

Detection, response, and defense for AI incidents.

amber track

RAG Security Track

Tenant boundary failures, authorization gaps, and retrieval leakage.

violet track

Agentic Workflow Track

Tool abuse, permission escalation, and workflow boundary failures.

emerald track

Governance Evidence Track

Evidence pack generation, control mapping, and audit readiness.

cyan track

Product Security Track

Secure SDLC, threat modeling, and AI supply chain.

Example Scenarios

Illustrative lab titles from across the catalog.

Prompt Injection Fundamentals
Prompt Injection
Indirect Prompt Injection via Documents
Prompt Injection
RAG Tenant Boundary Failure
RAG Authorization
Agent Tool Abuse: Unauthorized Send
Agentic Permissions
Sensitive Data in Context Window
Data Exposure & Privacy
Missing AI Incident Runbook
Incident Response
Output Monitoring and Detection Design
Detection Engineering
Evidence Pack Generation
Governance Evidence

Earn Domain Badges

Complete a lab track to earn the corresponding AIPSA domain badge. Badges are verifiable and shareable, demonstrating applied skills in each area.

View Badge Catalog →

Pair labs with certification

Lab tracks build applied knowledge aligned to AIPSA assessment domains. The two reinforce each other across every domain.