1,334 tagged Security, measured the same way as everything else here.
Browse within: claude-code-plugin 240compliance 107agentic-ai 91mcp-server 81fedramp 78devsecops 62model-context-protocol 62claude-plugin 61ai-tools 57ai-security 55claude-ai 53skills 51agents 48cursor 45
Plugin Claude Code
Bundles 2 skills, 4 commands, 1 agent · 186 tokens together
EU AI Act compliance scanner and trust infrastructure for Python AI projects.
Plugin Claude Code
Bundles 1 skill, 5 commands, 1 MCP server · 52 tokens together
Real-time safety scanning for LLM interactions. Detects prompt injection, PII leaks, harmful content, toxicity, obfuscation, secrets, and dangerous tool calls — 600-case benchmark at 100% accuracy with sub-millisecond latency.
VincentChuWaiChow/vanguard-frontier-agentic
Plugin Claude Code
Bundles 193 skills, 4 plugins · 11,995 tokens together
Cloud and zero-trust agentic workflow marketplace for skills, agents, rules, MCP references, and compliance-aware architecture.
Plugin Claude Code ✓ vendor
Bundles 3 skills · 534 tokens together
Technical AWS solutions for the problems startups get stuck on, from the AWS Startups Solution Architecture team. Multi-tenant SaaS isolation enforced in IAM rather than application code, and running a judgment agent such as an LLM reviewer inside a CI path. Startup here means the technical constraints are startup…
Plugin Cursor
Bring Trustabl's AI-agent safety & reliability scanner into Cursor — scan your agents, tools, and MCP servers, get a production-readiness score with severity-ranked findings, and fix issues before they ship.
Plugin Claude Code
Bundles 2 skills · 153 tokens together
Comprehensive security evaluation tools for agent skills and MCP servers with integrated GitHub and Bright Data access.
Myr-Aya/GouvernAI-claude-code-plugin
Plugin Claude Code
Bundles 1 skill, 1 command, 1 hook · 117 tokens together
Achieve flow state safely with Claude Code. Auto-approves routine work, gates risky actions, hard-blocks dangerous patterns. Dual enforcement (skill + hooks), token cap for cost governance, full audit trail. Zero dependencies.
Plugin Claude Code
Bundles 16 skills · 1,498 tokens together
The AI pentest co-pilot that actually finds bugs. Phase-chained, evidence-gated offensive security skills for bug bounty and authorized pentesting.
Plugin Cursor
Bundles 1 skill · 120 tokens together
Skarn for Cursor: audit your AI coding sessions and assistant configs for leaked credentials and risky configuration, and run the pre-execution guard. Backed by the Skarn detection engine on your machine; the skarn binary is installed separately. It declares one local MCP server, named skarn, with four tools (scansess.
Plugin Claude Code
Bundles 34 skills, 4 MCP servers · 626 tokens together
Offline AI/LLM security scanner: prompt injection, MCP command injection and tool poisoning, RAG leaks, poisoned Agent Skills. Scan code, or check a skill/MCP server before you install it.
sonnysangha/Vibe-Code-the-Right-Way-Ep-1-Indeed-Clone-Multi-Tenant-Clerk-Convex-MCP
Plugin Claude Code
Bundles 1 skill · 52 tokens together
Clerk Organizations for B2B SaaS - create multi-tenant apps with org switching, role-based access, verified domains, and enterprise SSO. Use for team workspaces, RBAC, org-based routing, member management.
Plugin Claude Code
Bundles 9 skills, 2 agents · 1,032 tokens together
OpenText Fortify AppSec skills. Use for SAST/DAST/SCA scanning, vulnerability triage, audit workflows, CI/CD pipeline integration, and FCLI commands. Supports Fortify on Demand (FoD) and Software Security Center (SSC).
Plugin Claude Code
Bundles 1 skill · 296 tokens together
A document-privacy tool that replaces identifying information locally before a document is sent to an AI model, then restores the original values in the response.
mohdhaji87/payloadsallthethings-skills
Plugin Claude Code
Bundles 61 skills · 1,398 tokens together
61 comprehensive security testing skills covering SQL injection, XSS, SSRF, XXE, SSTI, JWT attacks, OAuth, CORS, file upload bypass, deserialization, and more. Based on PayloadsAllTheThings repository for authorized penetration testing and security assessments.
Plugin Claude Code
Bundles 6 skills · 641 tokens together
OWASP API Security Top 10 skills for AI coding agents: BOLA detection, auth and RBAC scaffolding, injection checks, security test generation, full API security review, and OpenAPI schema hardening.
Plugin Claude Code
Bundles 1 skill, 1 command, 4 hooks · 61 tokens together
Universal developer safety guardrails — blocks dangerous commands, verifies builds, provides session context, and scans repo health.
Plugin Claude Code
Plugin marketplace listing 1 plugin: soundcheck.
Plugin Claude Code
Bundles 2 skills, 5 hooks · 51 tokens together
Production safety hooks for autonomous Claude Code operation. Context monitoring, syntax checking, branch protection, activity logging, and more.
Plugin Claude Code
Bundles 18 skills, 3 hooks, 1 MCP server · 913 tokens together
The kernel is the part that doesn't believe the agents. Bundles the DOS hooks (verify-on-stop, deny-a-refused-call, re-surface-a-stalled-stream), the DOS MCP server (verify / arbitrate / refuse-with-a-reason as tools), and the generic skill pack — one install. Requires the dos-kernel Python package: pip install 'dos.
Plugin Claude Code
Bundles 4 skills · 106 tokens together
Auxiliary skills for threat modeling - with and without OWASP pytm.
datumbrain/claude-code-privacy-guard
Plugin Claude Code
Privacy guard plugin for Claude Code - prevents PII and secrets from leaking into AI prompts.
Plugin Claude Code
Bundles 9 skills, 24 commands, 2 agents, 4 hooks · 4,114 tokens together
Elliot — offensive security engagement plugin with Hexstrike MCP integration for Kali Linux. Provides slash commands, auto-activating skills, and subagents for systematic penetration testing workflows.
Plugin Claude Code
Cyberbro IOC analysis toolkit. Extract, enrich, and analyze observables with 5 MCP tools.
Plugin Claude Code
Bundles 2 skills, 1 agent, 2 MCP servers · 175 tokens together
Validate VAST, VMAP, and DAAST ad tags against IAB Tech Lab specs. Hosted MCP at https://vastlint.org/mcp. Auth none for public tools.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: