Skill UI

This skill outlines a systematic, multi-phase workflow for diagnosing hard bugs and performance regressions in complex codebases. It emphasizes the critical necessity of building a tight, deterministic feedback loop (Phase 1) before moving to hypothesis generation. The process guides users through reproducing the failure, minimizing the scope of the issue, and forming actionable, ranked hypotheses.

Programmatically manage your entire contact database within Mailtrap. This guide covers using the API to create, update, delete, and bulk import contacts. It is essential for synchronizing contact data with CRMs, triggering custom automation events, building targeted segments, or performing large-scale list cleanups.

This guide outlines the comprehensive process of access recertification (or access review) using Saviynt Enterprise Identity Cloud. It details how to automate periodic validation of user entitlements to ensure adherence to the principle of least privilege. This function is critical for maintaining compliance with major standards such as SOX, SOC 2, and HIPAA. The process covers configuring various campaign types, managing the decision lifecycle (Approve/Revoke), and implementing remediation workflows.

A comprehensive tool designed to discover and map adversary-controlled assets, including C2 servers, phishing domains, and exploit kits. It utilizes sophisticated pivoting techniques across passive DNS records, Certificate Transparency logs, Shodan/Censys scans, and network fingerprints (JARM/JA3S) to generate actionable threat intelligence, perfect for CTI investigations and security operations.

This comprehensive guide details how to use industry-leading tools like TruffleHog and git-secrets to scan source code repositories, full git history, and configuration files for hardcoded AWS credentials and secrets. It is essential for integrating secrets detection into CI/CD pipelines, performing proactive security audits, and ensuring compliance by preventing sensitive keys from reaching production environments.

This skill provides a repeatable assessment for RAG systems, testing for critical vulnerabilities in vector stores and embedding models. It specifically addresses embedding inversion, cross-tenant data leakage, and knowledge-base poisoning, aligning with OWASP LLM08:2025. Use when performing authorized security audits of retrieval layers and multi-tenant isolation.

A powerful offensive suite for authorized red-teaming of Microsoft Entra ID (Azure AD). ROADtools combines ROADrecon for comprehensive directory enumeration (users, groups, policies, apps) and an offline GUI, with roadtx for advanced token acquisition, exchange, and Primary Refresh Token (PRT) abuse. It covers the full scope of cloud identity discovery and token-based attacks against highly regulated tenants.

This guide details using the comprehensive AADInternals PowerShell toolkit for defensive validation of Microsoft Entra ID, Azure AD, and AD FS environments. It covers unauthenticated tenant reconnaissance, acquiring access tokens for multiple Microsoft APIs, and critically, testing for federation backdoors (Golden SAML) by simulating advanced attack techniques (MITRE T1606.002). It is designed for authorized red-team assessments to map external attack surfaces and validate identity infrastructure hardening.

This skill audits Model Context Protocol (MCP) servers to detect critical AI security vulnerabilities. It scans for tool poisoning, tool shadowing, rug pulls, SSRF, and unauthenticated exposure. Use it before integrating new tools or during security reviews to ensure agent reliability and prevent supply chain attacks.

Falco is a powerful CNCF project for real-time runtime security monitoring. This guide teaches authors how to write and deploy custom detection rules using Falco's robust YAML rule engine and modern eBPF driver. It is designed to detect critical threats such as container escapes, namespace manipulation, privileged mounts, and anomalous syscalls in Kubernetes and Docker environments, significantly hardening the overall container security posture.

This skill provides advanced threat hunting queries for Microsoft Sentinel/Log Analytics. It detects the behavioral and string fingerprints left by popular offensive Entra ID enumeration tools (like ROADtools, AADInternals, and AzureHound) within both MicrosoftGraphActivityLogs and AADGraphActivityLogs. Use this when investigating suspicious Graph API activity, identifying internal reconnaissance, or building detection rules to surface active intrusions.

A specialized, read-only tool designed for penetration testing and red teaming. It performs comprehensive enumeration across AWS and Azure, allowing users to build a deep situational awareness of an environment. Key functions include identifying internet-exposed endpoints, retrieving sensitive secrets, and mapping critical trust relationships (like sts:AssumeRole) necessary for planning lateral movement or privilege escalation.