Security

majiayu000 Bundle

Build or audit a literature review. Use for evidence maps, gap analysis, contribution checks, source verification, and synthesis planning.

majiayu000 Bundle

Run a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistration, and replication readiness.

majiayu000 Bundle

Audit fielded survey response data for registered elements, data quality, bot and AI-automation screening, and sample integrity. Emits an appendix-ready quality report.

majiayu000 Bundle

Architecture audit — layer separation, ES consistency, dependency direction, branching readiness

majiayu000 Bundle

Audit and refactor CLAUDE.md files to eliminate bloat, enforce context engineering best practices, and create folder-level CLAUDE.md files for complex domain-specific instructions.

majiayu000 Bundle

Audit plugin implementations for registry trust rules, metadata validity, and ADR contract compliance.

majiayu000 Bundle

Review Convex code for security, runtime correctness, performance, schema design, and AgentForge-specific architectural boundaries.

majiayu000 Bundle

Verify code-review or security-review findings for false positives using deep codebase tracing, framework-aware analysis, and web research. Produces a .verified.md report alongside the original. Use when a review report has been generated and needs independent verification, or when user runs /verify-findings, mentions "verify review", "check false positives", or "validate findings".

majiayu000 Bundle

Extract endpoints, secrets, and hidden routes from JavaScript files using LinkFinder, SecretFinder, JSluice, and source-map analysis. Use when the user has live hosts and needs to mine the JS for attack surface that's not visible in the UI.

majiayu000 Bundle

Orchestrate complex work with 4.6 “Sol” as the Codex lead. Use when the user explicitly asks to orchestrate, delegate, fan out, parallelize, assign subagents, obtain independent checks, or have Sol act as tech lead. Decompose work, route bounded tasks to role-based Codex subagents, preserve integration ownership, and synthesize verified results.

majiayu000 Bundle

Multi-layer virus scanning for Aminet packages. Signature-based detection, heuristic hunk analysis, boot block scanning, quarantine management, and scan orchestration. Use when scanning packages, checking virus status, or managing quarantine.

majiayu000 Bundle

Clerk managed authentication - ClerkProvider, middleware, pre-built components, hooks, server-side auth, organizations, webhooks

majiayu000 Bundle

Authentication and authorization including JWT, OAuth2, sessions, and RBAC. Activate for login, auth flows, security, access control, and identity management.

majiayu000 Bundle

Use at the START of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next. Master orchestrator that combines the 5-phase non-linear hunting workflow with the critical thinking framework (developer psychology, anomaly detection, What-If experiments). Routes to all other skills based on current hunting phase. Also use when asking "what should I do next" or "where am I in the process."

majiayu000 Bundle

Patterns and best practices for Better-T-Stack projects (TanStack Router, Hono, Drizzle, tRPC, Better Auth)

majiayu000 Bundle

<!-- Copyright (c) 2026 defconxt. All rights reserved. -->

majiayu000 Bundle

Audit and remediate CIS benchmark violations. Use automated tools to assess compliance and implement hardening recommendations. Use when meeting compliance requirements or implementing security baselines.

majiayu000 Bundle

Advanced software engineering — systems programming, exploit development tooling, automation scripting, network programming, cryptography implementation

majiayu000 Bundle

Vulnerability assessment, defensive programming, and attack prevention

majiayu000 Bundle

Test AI training pipelines for data poisoning vulnerabilities and backdoor injection

majiayu000 Bundle

Debug and verify the three-layer defense against internal content leaking into user-visible messages.

majiayu000 Bundle

<!-- Copyright (c) 2026 defconxt. All rights reserved. -->

majiayu000 Bundle

Check endpoint security configuration for web properties

majiayu000 Bundle

Hunt NTLM/Negotiate information disclosure on internet-reachable IIS/SharePoint/Exchange. Anonymous NTLM Type-2 challenge capture leaks NetBIOS domain, internal DNS forest, computer name, AD timestamp via AV_PAIRS structure. Default Windows-installer hostnames (WIN-XXXXXXXXXXX pattern) signal lazy provisioning. Use when target advertises `WWW-Authenticate: NTLM` or `Negotiate` headers anonymously.

majiayu000 Bundle

Hunt WebSocket vulnerabilities — Cross-Site WebSocket Hijacking (CSWSH), missing authentication on WS handshake, message tampering, event authorization bypass, WS→HTTP request smuggling. Use when target has WebSocket endpoints (ws:// or wss://), real-time features, chat, live dashboard, or trading platforms.

majiayu000 Bundle

Purpose: Generate JWT verification middleware for FastAPI that validates Better Auth tokens.

majiayu000 Bundle

- Understanding input capture mechanisms for red team implants

majiayu000 Bundle

Mobile application penetration testing — Android/iOS static/dynamic analysis, Frida instrumentation, SSL pinning bypass, root/jailbreak detection bypass, deep-link abuse, exported components, insecure storage, biometric bypass

majiayu000 Bundle

Network penetration testing — lateral movement, pivoting, protocol attacks, traffic interception, Active Directory exploitation, wireless attacks

majiayu000 Bundle

Manage Cilium network policies: profile selection, access labels, Hubble debugging, platform namespace CNPs, and emergency escape hatch procedures. Use when: (1) Deploying a new application and setting network profile, (2) Debugging blocked traffic with Hubble, (3) Adding shared resource access, (4) Creating platform namespace CNPs, (5) Using the escape hatch for emergencies, (6) Verifying network policy enforcement. Triggers: "network policy", "hubble", "dropped traffic", "cilium", "blocked traffic", "network profile", "access label", "escape hatch", "cnp", "ccnp"

majiayu000 Bundle

OIDC flows, PKCE implementation, token refresh strategies, social login integration, and secure session management.

majiayu000 Bundle

AIエージェント向けガードレール定義(guardrails.md)を生成。権限境界・承認ゲート・監査証跡・エラー処理ポリシーを含む。

majiayu000 Bundle

SEC 2025 compliance validation for investment recommendations. Use when generating, reviewing, or auditing stock recommendations to ensure proper disclosures, audit trails, and regulatory requirements are met. Trigger on any recommendation generation or compliance review task.

majiayu000 Bundle

Agent Skill: Security audit patterns for PHP/OWASP. Use when conducting security assessments, identifying vulnerabilities (XXE, SQL injection, XSS), or CVSS scoring. By Netresearch.

majiayu000 Bundle

Configure and manage Claude Code security protections for sensitive files, credentials, and data. Use when the user invokes /security-setup to set up or modify protections against unauthorized file access, credential exposure, or sensitive data leaks.

majiayu000 Bundle

Application security patterns - authentication, secrets management, input validation, OWASP Top 10. Use when: auth, JWT, secrets, API keys, SQL injection, XSS, CSRF, RLS, security audit, pen testing basics.