Academy
AI Security Labs
Interactive training modules with embedded tools.
Fourteen AI security labs covering the full Map, Attack, Defend and Evidence workflow — from prompt injection and RAG data leakage to AI governance, threat modeling, and incident response. The first five labs embed interactive tools; the remaining nine are structured self-directed exercises with evidence templates and scoring checklists.
How it works
01
Read the brief
Each lab opens with the attack or defense concept, the underlying rules, and what you should observe.
02
Run the tool
Paste your own prompts, configs, or output — or use the provided fixtures. The tool runs deterministically with no LLM calls required.
03
Review findings
Findings are explained with the specific rule triggered, severity, and what an attacker or defender would do with this information.
Recommended path
Attack
Defend
Training modules
Foundation
Run 12 structured injection probes across 10 attack categories against a target system. Record outcomes, learn why each probe works, and export an evidence session.
Practitioner
Analyze system prompts against 15 security rule categories. Learn to spot secret leakage, instruction injection risks, KB corpus contamination, and weak policy patterns.
Practitioner
Test model output across 8 dangerous sink types — HTML, Markdown, JSON, tool calls, email, DB queries, code execution, and raw display. Learn why each sink is dangerous.
Practitioner
Analyze agent tool configurations for permission scope creep, missing approval gates, unsafe execution identities, and dangerous side effects. Works with MCP tool schemas.
Practitioner
Analyze RAG pipeline configurations for authorization gaps, tenant isolation failures, stale permission risks, and indirect injection surfaces. Paste a pipeline config and get findings.
Advanced
Trace how RAG pipelines leak tenant data and PII across retrieval scopes, vector metadata, and completion logging. Build a customer-safe exposure summary with evidence documentation.
Practitioner
Analyze three real supply chain attack artifacts — a malicious PR with a hidden HTML comment, a terraform state file with exposed secrets, and a poisoning attack pack — to map how AI supply chain attacks enter production.
Advanced
Analyze poisoned session history and memory artifacts to identify how attackers persist cross-session behavior changes. Classify attack types, trace influence paths, and map controls.
Advanced
Analyze adversarial payloads embedded in ASCII art, invisible unicode, SVG, and image metadata to understand how multimodal AI pipelines are hijacked across parse boundaries.
Foundation
Map AI system capabilities to a governance policy, identify coverage gaps, and produce a risk acceptance statement aligned to your organization's risk tolerance.
Practitioner
Build a complete AI system inventory record from a real MCP server configuration. Enumerate components, assign Keryn risk tiers, map data flows, and identify trust boundaries and provenance gaps.
Expert
Apply STRIDE to a real MCP server architecture. Place trust boundaries, enumerate all six threat categories, map sandbox escape vectors, and produce a threat model with specific controls at each enforcement point.
Practitioner
Evaluate AI telemetry coverage across prompt, completion, retrieval, and tool-use logs. Identify forensic evidence gaps and write an investigatability assessment.
Practitioner
Walk a real AI abuse incident from detection through after-action review. Classify the event, evaluate ethical incident drill scenarios, determine scope and containment, and produce an after-action report.
Keryn certification across four credential levels — scored, issued, verifiable.
View certificationStudy tools and printable course editions that cover each lab's domain.
Browse materialsTrack lab completions, scores, and certification readiness across all 16 labs.
View my progress