Skill UI

This guide provides advanced detection methods and threat hunting queries (KQL/SPL) to identify abuse of Azure service principals. It covers techniques such as privilege escalation, credential compromise, unauthorized role assignment, and enumeration, essential for SOC analysts and security teams monitoring Microsoft Entra ID.

A comprehensive guide and methodology for proactively hunting adversary abuse of legitimate cloud services (Azure, AWS, GCP, SaaS). This technique focuses on identifying Command and Control (C2), data staging, and exfiltration methods that leverage normal cloud functionality, making detection challenging.

This comprehensive pipeline guides users from a broad robotics direction to generating concrete, benchmark-grounded, and simulation-first research ideas. It orchestrates a four-stage workflow: literature survey, idea creation, novelty checking, and critical review. It systematically incorporates constraints like embodiment, task family, observation modalities, and simulation-to-real transfer feasibility, ensuring generated ideas are both novel and technically feasible for modern AI research.

This skill guides the implementation of network traffic baselining using historical NetFlow/IPFIX data. It leverages Python's pandas library to compute detailed statistical profiles, including hourly/daily distributions, per-host metrics, and protocol ratios. Anomalies are robustly detected using z-score and Interquartile Range (IQR) methods, assisting SOC analysts in identifying unusual activities like data exfiltration or beaconing.

A professional tool designed to draft comprehensive, structured academic papers in LaTeX format. It takes detailed outlines, research narratives, and figures, generating high-quality drafts tailored for specific top-tier venues (e.g., ICLR, NeurIPS, IEEE). Features include advanced citation management (DBLP/CrossRef) and structural style matching based on reference papers.

This skill orchestrates a complete, end-to-end pipeline for generating submission-ready academic papers. It takes a narrative draft or research outline and automatically progresses through planning, figure generation, section writing (LaTeX), compilation, and multiple rounds of automated review and refinement. The final output is a polished, structured paper with source files and a compiled PDF, perfect for publishing venues.

This guide details comprehensive physical security penetration testing techniques, essential for red teaming engagements. It covers methods such as tailgating, badge cloning (RFID), lock bypassing, and deploying rogue network devices (e.g., Pineapple, LAN Turtle). It provides practical toolkits and MITRE ATT&CK mapping to evaluate an organization's physical and digital control weaknesses.

A comprehensive guide and workflow demonstrating how to use YARA rules for proactive threat hunting. This method helps detect unknown malware, suspicious patterns, and Indicators of Compromise (IOCs) across filesystems, memory dumps, and network artifacts, making it essential for incident response and security analysis.

This skill provides a comprehensive, end-to-end pipeline for the entire academic research lifecycle. It guides users from initial idea discovery and experimental validation through rigorous cross-model review, culminating in a polished research paper draft. It supports advanced configurations, such as defining reviewer difficulty or integrating specific base code repositories, and allows for resumable runs.

Trivy is a comprehensive open-source vulnerability scanner used for detecting vulnerabilities, misconfigurations, secrets, and license violations across OS packages, language dependencies, and container images. It integrates seamlessly into CI/CD pipelines for robust security testing and compliance.

This module provides a centralized interface for the AgentHub message board. It allows multiple AI agents and the coordinator to communicate, track tasks, and log results through structured markdown posts across dedicated channels (Dispatch, Progress, Results). It is essential for monitoring complex multi-agent workflows and ensuring transparent collaboration and auditing.

Guides fine-tuning and evaluation of OpenVLA-OFT/OFT+ for robot action generation, covering LoRA adaptation, continuous action heads, FiLM conditioning, and LIBERO/ALOHA benchmarks plus deployment considerations.