#red-team

实战 SRC / 众测 / Bug bounty 漏洞挖掘 Claude Code skill — 19 个攻击类 playbook、305 个结构化 payload、263 个 WAF/EDR 绕过、2887 份 HackerOne 真实案例、88,636 WooYun 案例统计

Production-ready Claude Code skills for cybersecurity — secret scanning, SAST, prompt-injection testing, HTTP/JWT/dependency auditing. Zero dependencies.

Structured decision-making for Claude Code: a /method command, an auto-triggering methodology-driven-thinking skill, and a red-team-critic subagent over a shared 29-method index. Methods applied explicitly, not named.

Security testing skill for OS command injection and argument injection. Claude Code skill format.

Autonomous multi-agent AI penetration testing framework — 20 specialist agents, ECC architecture, MITRE ATT&CK + OWASP mapped, HMAC-chained audit trail, Docker sandbox, and multi-LLM backend (Ollama/OpenAI/Anthropic).

Source-backed archive of agent prompt-injection incidents, research records, trust-boundary patterns, schemas, and sanitized defensive summaries.

Multi-agent collaboration trust measurement & red-team verification (R0, F1, cost, L0-L3). Offline-reproducible Mock baseline for GOAI 2026 Agent Infra.

Offline regression tests and explainable release gates for RAG systems and AI agents.

SECS (SECurity aSsistant) turns an AI coding agent (Claude Code, Cursor, Codex) into an authorized information-security assistant - 35 security Agent Skills, a Debian/Ubuntu/Kali toolchain installer, and a local Metasploitable 3 practice lab, under strict rules of engagement.