Skill UI

This methodology allows engineers and analysts to conduct controlled counterfactual simulations when real-world testing (such as catastrophic failures, extreme load, or irreversible changes) is too rare, costly, or impossible. By isolating a single variable and tracing the mechanistic chain step-by-step, it helps surface critical system breakpoints, invariants, and necessary controls before deployment.

Coordinates authorized multi-stage security assessments including full penetration testing, external-to-domain compromise, and attack path planning. The skill acts as a central orchestrator, routing reconnaissance, initial access, privilege escalation, lateral movement, and reporting tasks to specialized sub-skills. Intended for authorized engagements only.

A comprehensive firmware and IoT penetration testing skill following OWASP FSTM. Covers firmware acquisition, static analysis, file system extraction with binwalk/unblob, automated EMBA scanning, system emulation via Firmadyne/QEMU, dynamic debugging, and binary exploitation for ARM/MIPS devices. Ideal for auditing routers, cameras, smart home devices, reproducing IoT CVEs, and discovering embedded 0-days.

This skill executes a comprehensive, three-stage verification pipeline to rigorously evaluate any given code artifact or execution session. The process starts with mechanical checks (linting, building, unit testing), progresses to semantic evaluation (checking against acceptance criteria and goal alignment), and optionally concludes with a Multi-Model Consensus vote for maximum reliability. Ideal for CI/CD pipelines and critical code reviews.

Hivemind is an advanced orchestration layer designed to manage complex tasks using a parallel swarm of external, low-cost workers. It simulates a structured team workflow (scout, coder, tester) to decompose large problems, execute subtasks in isolated worktrees, synthesize aggregated results, and perform consensus reviews. This dramatically reduces token costs and enhances reliability for large-scale coding, research, and testing tasks.

This methodology guides the development of new features, product slices, or integrations while mitigating the risk of overbuilding. It mandates an architecture-first approach, requiring the definition of clear acceptance criteria and explicit non-goals. The process focuses on delivering a coherent end-to-end path across responsible system layers, omitting unnecessary configuration, polish, or complexity, and halting immediately upon successful acceptance testing.

This agent provides comprehensive capabilities for managing the entire lifecycle of automated flows, including publishing, testing, performing batch operations, and generating detailed inventory reports. It covers the full scope from initial publication and validation to bulk management and health checks, ensuring stability and governance of workflow assets.

A comprehensive guide to conducting authorized security assessments across API-driven applications. This skill covers REST, gRPC, and WebSocket protocols, addressing the full OWASP API Security Top 10 2023. Techniques include identifying Broken Object Level Authorization (BOLA/IDOR), broken authentication, excessive data exposure, and implementing fuzzing for various API endpoints. Designed for professional penetration testing engagements.

A comprehensive guide detailing systematic techniques for breaking out of container isolation (Docker, Podman, containerd) into the underlying host operating system. Covers exploiting misconfigurations, abusing privileged modes, manipulating Linux capabilities (CAP_SYS_ADMIN), utilizing namespaces (nsenter), and exploiting known container runtimes CVEs. Essential for penetration testing and security red teaming engagements.

A systematic methodology for performing offensive cryptographic analysis. This skill focuses on identifying and exploiting flaws arising from the misuse of cryptographic primitives in real-world applications, rather than breaking the underlying math. Techniques covered include Padding Oracle Attacks (CBC), ECB block manipulation, Hash Length Extension, RSA weaknesses, and PRNG exploitation. Ideal for penetration testing and deep security auditing.

A deep-dive methodology for authorized penetration testing targeting dependency confusion and namespace resolution vulnerabilities across major package ecosystems (npm, PyPI, NuGet, Maven, etc.). This skill details advanced reconnaissance techniques, from analyzing lock files and source maps to exploiting error messages, alongside safe Proof-of-Concept (PoC) creation using DNS canaries for discovery during penetration engagements.

This guide provides comprehensive, battle-tested techniques for expanding access across a compromised network. It covers credential-based movement (Pass-the-Hash, Pass-the-Ticket), NTLM relay attacks, and remote execution protocols (WMI, WinRM). Used exclusively in authorized red team engagements and penetration testing, it details command sequences and OPSEC considerations required to reach high-value targets while minimizing detection.