hypnguyen1209/offensive-claude
8 subagents
Subagent
ai-researcherAI/ML research agent — model architecture analysis, training optimization, mechanistic interpretability, safety alignment, inference optimizationexploit-researcherVulnerability research agent — identifies CVEs, finds exploit PoCs, maps attack chains, and develops custom exploitation strategiesfinding-checkerBlind 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 finding-validatorAdversarial 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 acceptnetwork-analystDeep network analysis agent — packet inspection, protocol dissection, traffic anomaly detection, IDS/IPS rule creation, firewall auditingredteam-plannerRed team engagement planner — designs attack paths, C2 infrastructure, persistence strategies, and OPSEC considerations for authorized assessmentsreverse-engineerBinary analysis agent — disassembly, decompilation, vulnerability discovery in compiled code, firmware analysis, protocol reverse engineeringsecurity-reviewerDeep security audit agent — performs comprehensive security review of code, configs, and architecture against OWASP, MITRE ATT&CK, and CWE frameworks