Guides Active Directory and internal network penetration testing for AD enumeration, Kerberos abuse, relay attacks, ADCS exploitation, lateral movement, domain dominance, and MSSQL attacks in domain environments.
Guides JSON Web Token attack testing with algorithm confusion, signature bypass, header injection, and secret brute force techniques. Use when Bearer tokens, Authorization headers with eyJ prefix, or JWT cookies are observed during web or API testing.
Guides local and remote file inclusion testing with traversal payloads, PHP wrappers, log poisoning, and LFI-to-RCE chains. Use when parameters like page, file, include, or path accept filenames or traversal sequences.
Guides Linux penetration testing for privesc, persistence, container host escape, SUID/capabilities abuse, cron, kernel exploits, and post-ex on Linux sessions.
Guides macOS penetration testing when ROE includes macOS endpoints. Covers privesc, TCC bypass, keychain abuse, sandbox escape, launch daemon abuse, dylib hijacking, and XPC/Mach service abuse on Intel and Apple Silicon.
Central reference for pentest methodology, cross-cutting cheatsheets, reverse shells, file transfer, hash cracking, network discovery, and common tool syntax. Use during recon, threat modeling, post-exploit, and reporting when any domain skill needs quick operational references.
Guides Android and iOS application penetration testing including static/dynamic analysis, Frida hooking, certificate pinning bypass, and common mobile vulns. Use when ROE includes Android, iOS, or hybrid mobile app testing.
Orchestrates Metasploit Cursor Harness MCP tools through recon, module check, exploit, handler, session, and post-exploitation phases. Use when running msfsearchmodules, msfrunexploit, msfrunauxiliarymodule, payload generation, or session management with ROE enforcement in this project.
Master guide for using the Metasploit Cursor Harness MCP server. Use when starting an engagement, choosing between MCP and shell, setting up ROE, or understanding the tool surface. Read this first before any Metasploit work.
Post-exploitation workflow using Metasploit MCP. Use when interacting with active sessions, running post modules, harvesting credentials, collecting loot, or cleaning up sessions.
Reconnaissance workflow using Metasploit MCP read tools. Use when mapping targets, searching for exploit modules, correlating services with vulnerabilities, or querying the Metasploit database.
Guides NoSQL injection testing with operator-based auth bypass, blind extraction, JavaScript injection, and MongoDB-specific payloads. Use when MongoDB backend, JSON body with operators ($gt, $ne, $regex), or NoSQL error messages are observed during web testing.
Routes pentest tasks to the correct harness skill based on engagement type, target platform, discovered services, or vulnerability class. Use when choosing which skill to load for a specific testing scenario.
Orchestrates PTES-aligned phases, gates, and subgates for pentest engagements. Each subgate links to a skill the agent must load and execute. Use when starting an engagement, advancing phases, completing subgates, or when the user asks about workflow, gates, checkpoints, or pentest methodology structure.
Guides persistence mechanism research and documentation for Windows, Linux, and RDP. Use during post-exploit when ROE authorizes persistence testing, or to document options without deployment.
Guides network pivoting and tunneling including SSH tunnels, chisel, ligolo-ng, proxychains, Meterpreter routing, and port forwarding during post-exploitation. Use when reaching unreachable in-scope subnets from a foothold host.
Guides prompt injection testing with direct/indirect injection, jailbreak techniques, tool abuse, and system prompt extraction. Use when LLM chatbot features, AI-powered search, or text generation from user input are discovered.
Guides OPSEC, EDR evasion, and defensive control bypass including AMSI, AppLocker, ETW patching, process injection, PPID spoofing, and living-off-the-land techniques. Use before noisy actions or when encountering AV/EDR controls.
Guides vulnerability report writing and finding documentation including severity rating, evidence standards, and report structure. Use during report phase (SG6) and when structuring harness evidence into client deliverables.
Guides HTTP request smuggling testing with CL.TE, TE.CL, TE.TE, and H2 downgrade detection and exploitation. Use when front/back-end proxy chains or HTTP/2 downgrade scenarios are suspected in the target architecture.