Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). Runs on a local LLM behind a Privacy Gateway. Integrates with GitHub, GitLab, Jenkins, VS Code, JetBrains, n8n, Grafana & Splunk.
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an Ansible / AWX / Automation Controller configuration-management plane (inventories, playbooks, Vault, become, AWX REST API).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an Amazon Web Services account (IAM/STS/S3/EC2/Lambda/ECS/EKS/API-Gateway/Cognito/Secrets/RDS/CloudFormation/metadata).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Microsoft Azure resource plane (subscriptions/RBAC/managed-identities/VMs/Storage/KeyVault/AppService/Functions/AKS/SQL/Automation/ARM).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an enterprise backup platform (Veeam/Commvault/Rubrik/Cohesity/Veritas/Nakivo/Bacula/Restic/Borg: credential stores, repositories, restore-as-exfiltration).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for enterprise business platforms (Salesforce, ServiceNow, Atlassian Jira/Confluence, SharePoint on-prem, Nextcloud).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a container platform layered on Kubernetes (OpenShift routes/SCC/BuildConfig/OAuth/internal registry, Rancher management plane/API keys/Fleet/downstream clusters).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for OCI/Docker container registries (Harbor, Docker Registry v2, GHCR, GitLab Registry, Quay, JFrog Artifactory, Nexus, ECR/ACR/GAR).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an exposed Docker Engine API (unix socket or unauthenticated TCP 2375/2376), images, containers and container-to-host escape.
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed Darkmoon toolbox for Drupal applications (core, contrib modules, JSON:API, REST, Entity/Field system, Render API, Twig, Views, Drupal Commerce, roles/permissions).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an edge and reverse-proxy tier (Cloudflare/Nginx/HAProxy/Traefik/Envoy/F5-BIG-IP/Citrix-ADC: origin discovery, admin planes, request smuggling, cache poisoning, WAF bypass).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for mail infrastructure (Exchange on-prem Autodiscover/EWS/OWA/ECP, Postfix/Exim/Dovecot, SMTP relays, SPF-DKIM-DMARC spoofing, mailbox data mining).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for Microsoft Entra ID (Azure AD) identity: users/groups/roles, applications & service principals, OAuth consent, app credentials, Conditional Access, Microsoft Graph, hybrid AD/Azure paths.
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for firewalls and network infrastructure (Palo Alto/Fortinet/Check Point/pfSense/Cisco ASA plus IOS/Juniper/Aruba/MikroTik gear plus BIND/PowerDNS/Infoblox/DHCP/IPAM management planes).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for embedded / IoT firmware and devices (firmware image extraction, hardcoded credentials & secrets, backdoors, embedded web/CGI/LuCI interfaces, insecure network services, outdated components — OpenWrt/BusyBox/Dropbear/uhttpd class devices).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for python-flask web application.
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Google Cloud Platform environment (IAM/service-accounts/impersonation/GCS/GCE/Functions/Run/GKE/SecretManager/BigQuery/CloudSQL/metadata).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for GitHub / GitHub Enterprise (orgs, repos, PATs, GitHub Apps, Actions workflows, secrets, self-hosted runners, packages, branch protection).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for GitLab (SaaS/self-managed): groups/projects, permissions, CI/CD variables, pipelines, runners, artifacts, registry, deploy & access tokens, webhooks, K8s agent.
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a GitOps control plane (ArgoCD/FluxCD/Tekton/Crossplane, their controllers, repo and cluster credentials, and the git-to-cluster pivot).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for Go (Gin / Echo / Fiber / Beego / net-http) web applications.
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for graphql application.
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a HashiCorp Vault instance (auth methods/policies/token abuse/secrets engines KV-PKI-transit-database/leases/namespaces/unseal).
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for web application navigation with headless browser.
Agent Claude Code
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a virtualization control plane (VMware vSphere/vCenter/ESXi, Proxmox VE, Microsoft Hyper-V, Nutanix Prism, Citrix Virtual Apps and Desktops).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: