Skill UI

An expert guide for deploying and optimizing Large Language Models (LLMs) entirely on local hardware. Mastering the entire local AI ecosystem, including inference engines like Ollama, vLLM, and llama.cpp. Provides deep knowledge on quantization formats (GGUF, EXL2, AWQ), VRAM calculation, and ensuring privacy-first, offline deployment for state-of-the-art models.

This skill provides methods for reliably extracting typed, validated, and structured data from Large Language Models (LLMs), moving beyond simple text parsing. It covers best practices across major APIs (OpenAI's response_format, Anthropic's tool_use, Google's responseSchema) and local models. Key workflows include defining schemas (Pydantic/Zod), implementing constrained decoding, and building robust retry loops for production-grade data pipelines.

This skill guides the process of analyzing Windows Prefetch (.pf) files to reconstruct a detailed program execution history. By parsing these system artifacts, users can determine which applications were run, how many times, and when. It is crucial for building forensic timelines, confirming suspicious binary execution during malware investigations, and localizing evidence in a Windows system.

This tool provides a comprehensive framework for analyzing web server logs (Apache/Nginx) to detect various security threats. It uses advanced regex matching against OWASP attack signatures to identify SQL injection, Local File Inclusion, and Directory Traversal attempts, alongside behavioral analysis for brute-force attacks and web scanner fingerprints. The system also enriches data using GeoIP for source attribution, generating a prioritized report for SOC analysts.

A comprehensive guide for conducting penetration testing on iOS and Android mobile applications, adhering to the OWASP MASTG. This skill covers the full mobile attack surface, including static analysis of binaries, dynamic runtime testing, and deep API security assessment. Techniques taught include bypassing certificate pinning, analyzing local data storage (Keychain, SQLite), and identifying vulnerabilities in authentication and network communication.

This skill provides a comprehensive guide for identifying and exploiting insecure local data storage vulnerabilities in Android and iOS applications. It covers analyzing plaintext credentials, unencrypted SQLite databases, insecure SharedPreferences, and improper keychain/keystore usage. Essential for performing robust mobile penetration testing focused on OWASP M9.

This skill guide details the implementation of envelope encryption using AWS Key Management Service (KMS). It outlines the secure process of using a Data Encryption Key (DEK) to encrypt data locally, and subsequently protecting that DEK with a KMS-managed Key Encryption Key (KEK). This method is crucial for encrypting large data volumes on AWS, significantly reducing direct KMS API calls, improving performance, and maintaining compliance with strict security standards.

This skill covers performing comprehensive vulnerability assessments across diverse environments, including on-premises infrastructure, cloud VMs, and container registries. It leverages standard network protocols like SSH (Linux) and WMI (Windows), coupled with advanced cloud provider APIs for analyzing disk snapshots without requiring local endpoint agents. Ideal for security auditing and compliance checks.

This guide details how to configure and execute deep, authenticated vulnerability scans using OpenVAS/Greenbone Vulnerability Management (GVM). By utilizing valid credentials (SSH, SMB, or ESXi), users can log into target systems to detect local vulnerabilities, missing security patches, and misconfigurations, which are typically missed by unauthenticated scans. Essential for professional security auditing and penetration testing.

This guide details how to perform authenticated (credentialed) vulnerability scans using industry-leading tools like Nessus, Qualys, and OpenVAS. By utilizing service credentials (SSH, SMB, WinRM, SNMPv3), the scan moves beyond superficial banner checks to deeply inspect installed patches, configurations, and local system settings on Linux, Windows, and network devices. This is crucial for detecting vulnerabilities that unauthenticated scans often miss, significantly improving security assessment accuracy.

This comprehensive guide details methods for testing web applications against directory traversal (path traversal) and local/remote file inclusion (LFI/RFI) vulnerabilities. It covers advanced techniques, including path manipulation, encoding bypasses, and automated fuzzing using tools like ffuf and dotdotpwn. Use this during authorized penetration tests to assess file download, view, or include functionality.

This tool facilitates interactive dynamic malware analysis using the ANY.RUN cloud sandbox. It allows analysts to detonate suspicious samples, observe real-time execution behavior, and manually interact with prompts (like dialogs or CAPTCHAs). Key outputs include detailed process trees, network traffic analysis (C2 communication), and identification of all Indicators of Compromise (IOCs), mapping observed behaviors to MITRE ATT&CK. Essential for rapid, sophisticated behavioral analysis without maintaining local sandbox infrastructure.