Skill UI

A comprehensive guide for conducting authorized vishing (voice phishing) pretext calls. This technique, utilized in red-teaming, simulates an attacker impersonating a trusted authority (e.g., IT support, vendor) to test an organization's human security controls. It measures employee adherence to verification protocols and highlights vulnerabilities in staff security awareness.

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.

This skill provides a comprehensive, cross-platform workflow for auditing UEFI firmware security. It detects advanced threats like bootkits (e.g., BlackLotus, Bootkitty) and Secure Boot bypasses by verifying the integrity of the platform's trust chain. Key checks include confirming Secure Boot status, assessing the currency and application of DBX revocations, and examining the protection of critical EFI variables using specialized tools. Essential for hardware security assessments and forensic investigation.

CloudFox is an open-source, attacker-centric tool designed for authorized cloud penetration testing. It maps attack paths and identifies exploitable misconfigurations across AWS and Azure environments. By simulating an attacker's perspective, it goes beyond simple configuration audits to reveal critical assets, exposed secrets, and lateral movement opportunities (like STS AssumeRole trust relationships), providing comprehensive situational awareness for security assessment.

This skill utilizes NVIDIA's open-source garak framework to conduct comprehensive red-teaming assessments on Large Language Models (LLMs). It tests for critical vulnerabilities such as prompt injection, jailbreaks, data leakage, and toxic content generation by sending thousands of adversarial probes. Ideal for pre-deployment security validation, API guardrail testing, and generating defensible evidence for AI risk assessments.

A comprehensive skill for managing AWS operational excellence, cost governance, and observability. It provides guidance on pre-deployment cost estimation (TCO), detailed spending analysis using Cost Explorer, setup of CloudWatch alarms, auditing activity via CloudTrail, and overall security posture assessment. Essential for optimizing cloud spending and ensuring reliable infrastructure.

This comprehensive tool performs an architectural audit of a codebase, mapping module dependencies, checking layering integrity, and flagging structural decay. Drawing on classic engineering principles (like Conway's Law and Testability Seams), it provides a deep assessment of the project's health and structure. Ideal for large-scale code reviews or onboarding new developers.

This skill provides a comprehensive tech debt assessment, identifying, classifying, and prioritizing core maintainability issues. By drawing on classic engineering principles, it helps teams build a structured refactoring roadmap, optimizing code health and development velocity.

This advanced skill performs a full-sweep analysis, providing a unified assessment of code quality across multiple dimensions: code decay, architecture integrity, technical debt, and test coverage. It automatically applies safe fixes directly to the codebase, while requiring confirmation for risky changes. It is ideal for comprehensive pre-release code health audits and automated refactoring.

This skill guides users through the complete lifecycle of data quality incident management using Monte Carlo MCP tools. It performs detailed investigation, including root cause analysis and blast radius assessment. It then coordinates various external tools (APIs, CLI) to propose and execute appropriate remediation actions, ensuring all data incidents are resolved with full context.