Security

pentrestion/capybara-nexus-v2

Skill Claude CodeCodex

Name: capybara-nexus-v2 Tier: Frontier (Capybara-class) Mandate: Autonomous Reasoning, Empirical Feedback, & Zero-Day Research.

r3352/redact-mcp

Plugin Claude Code

Bundles 3 skills, 2 hooks, 2 MCP servers · 36 tokens together

Auto-obfuscates sensitive client data during pentesting so Claude never sees real PII, hostnames, or credentials.

telus-labs/stagecraft

Skill Claude CodeCodex

Run a structured codebase audit — map architecture, assess health (compliance / tests / docs), perform deep analysis (security / performance / code quality), and synthesize a prioritized roadmap. Use this skill when the user says things like 'audit the codebase', 'understand this project', 'find problems', '/audit'…

JoviDeCroock/skills

Skill Codex

Use when hardening npm package release workflows with trusted publishing, OIDC, GitHub environments, pinned GitHub Actions, disabled publish-path caching, Changesets release PRs, direct tag-based npm publish flows, staged publishing, or npm release-supply-chain reviews.

vulnersCom/vulners-mcp

MCP server Claude CodeCodexCursor +2

MCP interface server fronting the Vulners API (https://vulners.com). Runs locally from the vulners-mcp Python package.

ArmisSecurity/armis-appsec-mcp

Skill Claude CodeCodex

On-demand AI-powered security scanning. Use when the user asks to scan code for vulnerabilities, run a security check, scan code for security issues, scan a file, scan a diff, scan staged changes, check for security issues, check for secrets, find hardcoded credentials, or run an appsec scan. Triggers: /security-scan…

suyogpawar88/Threat-Model

Cursor rule Cursor

End-to-end security threat modeling (STRIDE/PASTA, OWASP AppSec/API/LLM Top 10, MITRE ATT&CK/ATLAS) for AI and conventional application infrastructure, using this repo's Jira/Jenkins/ServiceNow/repo connectors.

Dhirenderchoudhary/unmarkk

Skill Claude CodeCodex

Inspect and remove identifying metadata and provenance marks from files — GPS coordinates, camera serial numbers, author names, editing timestamps, C2PA content credentials, and invisible Unicode carriers. Works on PNG, JPEG, WebP, PDF, DOCX, ODT, SVG, HTML, Markdown and plain text. Use when someone asks to strip…

Bhanunamikaze/Code-VulnScan-Skill

Skill Claude CodeCodex

Use this when the user wants to find security vulnerabilities in a codebase, perform a security audit, scan for CVEs, detect secrets, review React/Next.js, Go, Java/Kotlin JVM, PHP, Ruby, .NET, or Rust web services, audit architecture/application/infrastructure flaws, review auth/API/crypto/business logic, check…

popoloni/non_deterministic_sw_eng

Cursor rule Cursor

When writing code that handles authentication, authorization, or sensitive data.

ryanda9910/crucible

Skill Claude Code

Review code for correctness, security, TypeScript quality, and performance. Run before any PR or deploy.

noloman/Android-AI-skills

Skill Claude CodeCodex

Skill "android-auth-identity" from noloman/Android-AI-skills, covering android authentication & identity, hard rules, core patterns and references.

LeoKemp223/embedded-llm-guardrails

Skill Claude CodeCodex

Safety instructions for using an AI coding assistant in embedded projects, such as microcontroller, real-time operating system, driver, and board-support code. Embedded software runs on dedicated hardware, where mistakes can affect the device itself.

Contoso-State/red-team-agent-orchestration

Cursor rule Cursor

Coordinates an Azure cloud-security red team assessment end to end. The user interacts with this agent; it validates engagement scope, dispatches the specialist sub-agents (recon, identity, authorization, network, compute, containers/Kubernetes, data, web, AI/Foundry, attack-surface/EASM, governance/posture…

proluct/skanna

Plugin Claude Code

Bundles 3 skills, 1 hook · 205 tokens together

Security-scan a Claude Code skill, plugin, or MCP server before installing it. SAFE / CAUTION / DANGEROUS verdict with file:line findings. Read-only, never executes the target.

macaugh/super-rouge-hunter-skills

Skill Claude Code

Systematic methodology for developing reliable exploits from vulnerability discovery to weaponization.

killvxk/malskills-zh

Plugin Claude Code

Bundles 120 skills · 9,711 tokens together

Offensive security skills collection for authorized penetration testing, CTF challenges, and security research. Includes tools for reconnaissance, exploitation, C2 frameworks, evasion, reverse engineering, and programming patterns.

lacework/forticnapp-llm-plugins

Plugin Claude Code

Bundles 3 skills, 4 hooks · 65 tokens together

Fortinet Code Security — IaC and SCA scanning for Claude Code.

thesaadmirza/blindfold

Plugin Claude Code

Bundles 1 skill, 2 hooks · 55 tokens together

Blindfolds the LLM from your secrets. Stores API keys, tokens, and passwords in your OS keychain. The LLM works with placeholders, never sees actual values. Kernel-level sandbox enforcement on macOS.

tendhearth/wechat-cc

Skill Claude Code

Manage WeChat channel access — edit allowlists and set DM policy. Use when the user asks to add/remove users, check who's allowed, or change policy.

el95149/rapid7-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server "rapid7-mcp-server" as configured in el95149/rapid7-mcp-server. Runs locally from the rapid7-mcp-server npm package.

mbeato/APIMesh

MCP server Claude CodeCodexCursor +2

MCP server for APIMesh — 76 x402-payable tools for AI agents (74 APIs + wallet usage + spend caps). Covers web vitals, security headers, SEO audits, email security and verification, tech-stack detection, brand assets, redirect chains, indexability, brand. Runs locally from the @mbeato/apimesh-mcp-server npm package.…

liangjunyu2010/mcp_server_safe_content_check

MCP server Claude CodeCodexCursor +2

MCP server "mcp-server-safe-content-check" as configured in liangjunyu2010/mcpserversafecontentcheck. Runs locally from the mcp-server-safe-content-check Python package.

YoussefSahnoun/PentestMCP

MCP server Claude CodeCodexCursor +2

This is an MCP server that exposes red team tools for active directory pentesting to LLMs. Runs locally from the pentestMCP Python package.