Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Skills

Each agent’s deep methodology is an auto-loaded skill under .github/skills/azure-redteam-*, discovered automatically by its description. Skills give every agent its methodology and read-only az runner without manual wiring.

Skill map

SkillWhen the runtime uses it
azure-redteam-orchestratorPentest Manager. “Run a red team assessment”, “pentest my Azure environment”
azure-redteam-inventoryPreflight recon — permission validation + resource enumeration
azure-redteam-identityEntra ID / authentication posture
azure-redteam-authorizationRBAC, privilege escalation, attack-path correlation
azure-redteam-networkPublic exposure, NSGs, segmentation
azure-redteam-computeVM, App Service, Function App, serverless compute security
azure-redteam-aks-containerAKS / Kubernetes RBAC & Pod Security, ACR, Container Apps/Instances + gated in-cluster scanning
azure-redteam-dataStorage, Key Vault, SQL / database protection
azure-redteam-webWeb edge/delivery: WAF, TLS, static sites, API Management
azure-redteam-aiAzure AI Foundry, OpenAI, Cognitive Services, ML
azure-redteam-easmExternal attack surface, dangling DNS, unknown assets
azure-redteam-loggingDetection & monitoring coverage
azure-redteam-governanceAzure Policy, Defender for Cloud posture, MG hierarchy, resource locks
azure-redteam-supplychainOIDC/federated credentials, pipeline SPs, ACR, automation, Logic Apps
azure-redteam-emailM365 email security (SPF/DKIM/DMARC, Defender for Office 365) — optional
azure-redteam-external-vulnGated active testing. OWASP Top 10 validation of Azure-discovered URLs/IPs + optional offline static analysis — scope-locked, off by default
azure-redteam-reportingNormalize findings, render deliverables

Agent ↔ skill ↔ runner

Each skill stays thin and delegates to a single source of truth:

This keeps the skill, the agent, and the checks in lock-step without duplicating content.

Agent fileDisplay nameInvoked by
redteam-orchestrator.agent.mdRed Team Orchestrator (Pentest Manager)User (/agent redteam-orchestrator)
redteam-inventory.agent.mdRed Team Inventory & ScopeOrchestrator
redteam-identity.agent.mdRed Team IdentityOrchestrator
redteam-authorization.agent.mdRed Team AuthorizationOrchestrator
redteam-network.agent.mdRed Team NetworkOrchestrator
redteam-compute.agent.mdRed Team Compute (VM / App Service / Functions)Orchestrator
redteam-aks-container.agent.mdRed Team Azure Container & Kubernetes (gated in-cluster lane)Orchestrator
redteam-data.agent.mdRed Team Data (incl. SQL/databases)Orchestrator
redteam-web.agent.mdRed Team Web & Static SitesOrchestrator
redteam-ai.agent.mdRed Team AI & FoundryOrchestrator
redteam-easm.agent.mdRed Team Attack Surface (EASM)Orchestrator
redteam-logging.agent.mdRed Team LoggingOrchestrator
redteam-governance.agent.mdRed Team Governance & PostureOrchestrator
redteam-supplychain.agent.mdRed Team DevOps & Supply ChainOrchestrator
redteam-email.agent.mdRed Team Email Security (optional, M365)Orchestrator
redteam-external-vuln.agent.mdRed Team External Vulnerability (EVA) (gated active testing)Orchestrator (only in external-active-testing mode)
redteam-reporting.agent.mdRed Team ReportingOrchestrator

See Methodology for the checks, playbooks, and knowledge base that the skills draw on.