Skill UI

This tool provides a comprehensive security assessment framework for Retrieval-Augmented Generation (RAG) systems and vector databases. It tests critical vulnerabilities such as embedding inversion, cross-tenant data leakage, knowledge-base poisoning, and retrieval manipulation, aligning with OWASP LLM08:2025 standards. It is essential for validating the security posture of multi-tenant and vector-search applications.

ROADtools is a comprehensive offensive toolkit for Microsoft Entra ID (Azure AD). It consists of ROADrecon for offline directory enumeration (users, groups, roles, policies) and roadtx for advanced token acquisition and exchange. It is designed for authorized red-teaming and penetration testing to discover attack paths and pivot tokens across various Microsoft resources.

This skill simulates advanced red-teaming techniques targeting Microsoft Entra ID's OAuth 2.0 device-code flow and illicit consent mechanisms. It demonstrates how attackers can steal access and refresh tokens, bypass Multi-Factor Authentication (MFA), and pivot across various Microsoft 365 services. It is designed for authorized security testing to validate token protection and conditional access policies.

This toolkit provides comprehensive offensive and administrative capabilities for Microsoft Entra ID, Azure AD, and AD FS. It allows authorized penetration testers to perform unauthenticated reconnaissance, acquire various access tokens, and critically, test for federation backdoors (Golden SAML). It is essential for validating identity-attack resilience and producing detailed hardening recommendations during red-team engagements.

This skill provides comprehensive security auditing for Model Context Protocol (MCP) servers and their associated tool metadata. It is designed to detect sophisticated supply chain attacks, including tool poisoning (indirect prompt injection), Server-Side Request Forgery (SSRF), tool shadowing, and unauthenticated exposure. It is essential for securing AI agent stacks before integrating new tools or during CI/CD processes.

CHIPSEC is an open-source framework designed to assess the low-level security configuration of x86 platform firmware and hardware. It verifies critical security controls such as SPI flash write protection, BIOS locks, SMM/SMRR configuration, and Secure Boot variable integrity. Users can run automated tests, dump SPI flash memories for forensics, and detect potential firmware implants that persist below the operating system layer.

An AI assistant for generating and analyzing Chinese Bazi (Four Pillars) and Ziwei Dou Shu charts using precise algorithms, supporting individual analysis, cross-validation, and structured report generation.

kube-bench is an open-source tool that validates the compliance and security posture of Kubernetes clusters. It rigorously checks control-plane components, worker nodes, and cluster policies against the comprehensive CIS Kubernetes Benchmark. It reports findings (PASS/FAIL/WARN) and includes specific remediation guidance, making it essential for compliance auditing and hardening efforts.

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.

A comprehensive tool and methodology for identifying and preventing dependency confusion attacks across major package ecosystems (npm, PyPI, Maven). It detects instances where internal, private package names are leaked and subsequently published publicly by attackers. The skill provides both detection (enumerating claimable internal names) and prevention strategies (enforcing registry pinning and scope restrictions) to secure the software supply chain.

This skill provides advanced threat hunting logic for Microsoft Sentinel/Log Analytics. It analyzes both AADGraphActivityLogs and MicrosoftGraphActivityLogs to detect the unique fingerprints and behavioral patterns left by offensive Entra ID tools (like ROADtools, AADInternals, and AzureHound). It detects specific User-Agent strings and characteristic endpoint-sweep patterns, even when tool authors attempt to spoof headers, helping SOC teams identify valid account-based adversary activity (MITRE T1078.004).

This skill provides methods and frameworks to detect sophisticated AI attacks, including model stealing, membership inference, and model inversion. It focuses on monitoring query patterns, analyzing confidence exposure, and implementing defensive controls on inference APIs to protect intellectual property and data privacy.