hypnguyen1209

hypnguyen1209/offensive-claude

Plugin Claude Code

Marketplace for the offensive-claude security-research framework.

hypnguyen1209/offensive-claude

Plugin Claude Code

Spec-driven offensive-security framework for Claude Code: 31 kill-chain skills, executable safety controls (scope/finding/OPSEC discipline), pattern-learning memory, and a bounded engagement engine — with a SessionStart dispatcher that enforces skill-invocation discipline.

hypnguyen1209/offensive-claude

Instructions file

Instructions for hypnguyen1209/offensive-claude, covering security research & offensive operations config, behavior, skills available, agents available and engagement workflow — cyber kill chain.

hypnguyen1209/offensive-claude

Agent

AI/ML research agent — model architecture analysis, training optimization, mechanistic interpretability, safety alignment, inference optimization.

hypnguyen1209/offensive-claude

Agent

Vulnerability research agent — identifies CVEs, finds exploit PoCs, maps attack chains, and develops custom exploitation strategies.

hypnguyen1209/offensive-claude

Agent

Blind adversarial checker — given ONLY a finding artifact and its evidence (never the author's reasoning), tries to refute it and emits a structured rebuttal that drives the bounded generator↔checker rebuttal loop. Distinct from finding-validator.

hypnguyen1209/offensive-claude

Agent

Adversarial exploitability judge — issues a PASS / KILL / DOWNGRADE / CHAIN-REQUIRED verdict on each finding, distinct from the artifact-completeness check. Tries to REFUTE every finding before accepting it.

hypnguyen1209/offensive-claude

Agent

Deep network analysis agent — packet inspection, protocol dissection, traffic anomaly detection, IDS/IPS rule creation, firewall auditing.

hypnguyen1209/offensive-claude

Agent

Red team engagement planner — designs attack paths, C2 infrastructure, persistence strategies, and OPSEC considerations for authorized assessments.

hypnguyen1209/offensive-claude

Agent

Binary analysis agent — disassembly, decompilation, vulnerability discovery in compiled code, firmware analysis, protocol reverse engineering.

hypnguyen1209/offensive-claude

Agent

Deep security audit agent — performs comprehensive security review of code, configs, and architecture against OWASP, MITRE ATT&CK, and CWE frameworks.

hypnguyen1209/offensive-claude

Command

Execute Phase 7 - Actions on Objectives and Goal Achievement.

hypnguyen1209/offensive-claude

Command

Execute Phase 6 - Command and Control Infrastructure Setup.

hypnguyen1209/offensive-claude

Command

Crash → root cause → reachability → empirical exploitability verdict (native bugs).

hypnguyen1209/offensive-claude

Command

Find the canonical fix commit(s) for a CVE across sources, then diff for root cause.

hypnguyen1209/offensive-claude

Command

Execute Phase 3 - Delivery and Payload Deployment.

hypnguyen1209/offensive-claude

Command

Execute Phase 4 - Exploitation and Access Establishment.

hypnguyen1209/offensive-claude

Command

Run gate validation on the current phase before proceeding.

hypnguyen1209/offensive-claude

Command

Initialize a new security engagement following the Kill Chain workflow.

hypnguyen1209/offensive-claude

Command

Execute Phase 5 - Installation and Persistence Establishment.

hypnguyen1209/offensive-claude

Command

Cross-engagement pattern memory — recall prior techniques, record confirmed findings, housekeeping.

hypnguyen1209/offensive-claude

Command

Resume an engagement from the engine trace — skip completed steps, continue where you left off.

hypnguyen1209/offensive-claude

Command

Execute Phase 1 - Reconnaissance and Attack Surface Mapping.

hypnguyen1209/offensive-claude

Command

Execute Phase 8 - Final Reporting and Engagement Closeout.