Security

snyk/agentic-integration-wrappers

Plugin Gemini CLI

MCP configuration declaring 1 server: snyk.

dennishavermans/agentfile

Plugin Claude Code

Bundles 1 skill, 1 hook · 51 tokens together

Catches agent configuration that grants more than it appears to: permission rules whose wildcards reach further than they read, broken skill references, and MCP servers that will silently fail to load.

DefaultPerson/agent-setup

Skill Claude Code

Load a compact snapshot of the current repository into context — structure, stack, docs, git state.

taslim/nanoclaw-gws-ea

Skill Claude CodeCodex

OneCLI Gateway: transparent HTTPS proxy that injects stored credentials into outbound calls. You MUST use this skill when the user asks you to read emails, check calendar, access GitHub repos, create issues, check Stripe payments, or interact with ANY external service or API. Do NOT use browser extensions or OAuth CLI…

sunglasses-dev/sunglasses

Plugin Claude Code

Bundles 1 MCP server

Local input firewall for AI agents. Scans text and files before an agent reads them. Needs pip install sunglasses first, on Python 3.9 or newer.

Aaditya1273/Agent.md

Skill Codex

Install, find, link, update and validate engineering standards from the Agent.md registry (304 free MIT markdown standards across 20 categories) using the activate-agentmd CLI; print the breaking changes for the dependency majors this project runs; and lint agent instruction files for leaked keys and prompt injection.…

getty104/claude-code-marketplace

Plugin Claude Code

Bundles 1 skill · 213 tokens together

A Bitwarden connection that provides stored login details only after approval, then puts them into commands or browser logins.

endorlabs/ai-plugins

Plugin Claude Code

Bundles 12 skills, 11 agents, 3 hooks, 1 MCP server · 1,662 tokens together

Endor Labs workflow agents and setup for Claude Code.

vyuh-labs/dxkit

Skill Claude Code

Read a dxkit report and execute fixes — prioritize findings by severity, plan the fix sequence, run the fix, verify the score moved, re-baseline if appropriate. Supports a SCOPED pass to burn down one category at a time (dependency/BOM vulnerabilities, security, code quality, tests, docs), and a BASELINE-CLEANUP pass…

mantacron/manta

Agent Claude Code

Full security audit agent. Checks for OWASP Top 10 vulnerabilities, hardcoded secrets, vulnerable dependencies, injection flaws, broken authentication, insecure data exposure, SSRF, path traversal, and more. Use on any code change — always runs in pre-commit pipeline.

ChainAware/behavioral-prediction-mcp

Skill Codex

Use this skill whenever a user asks about wallet safety, fraud risk, rug pull detection, wallet behavior analysis, DeFi personalization, on-chain reputation scoring, AML checks, token ranking by holder quality, airdrop screening, lending risk, token launch auditing, or AI agent trust scoring. Triggers on questions…

asap-protocol/agentic-orchestration

Command Claude CodeCursor

You are a senior security engineer conducting a focused security review of the changes on this branch.

zhangyu94/humanfile

Cursor rule Cursor

Respect .human file boundaries - check protection levels before editing any file.

Michae2xl/freedom-stack

Skill Claude CodeCodex

Agent Shielded — Agent Privacy Cloud. Private infrastructure for AI agents in one command: Ollama, n8n, Qdrant, Agent Sandbox, Tor Rotator, Privoxy, Gotify, Agent Dashboard + Prometheus, Grafana, Portainer. Zero data leaks. Triggers: 'agent shielded', 'agent privacy', 'AI agent infrastructure', 'private LLM', 'Ollama…

TheDarkMist/nis2-incident-report

Skill Claude CodeCodex

Drafts NIS2 incident reports for a small WordPress agency or freelancer, especially one acting as supply chain to a regulated client rather than as a regulated entity itself. Use this skill whenever someone needs to draft or produce a NIS2 incident notification: a 24-hour early warning, a 72-hour notification, a…

the-missing-pink/ai-repository-security-baseline

Cursor rule Cursor

Security rules for preventing secret leakage, injection vulnerabilities, and unsafe code patterns.

sjhhh024-cmyk/Spider-JS-Mcp-Skills

Skill Claude CodeCodex

A general-purpose guide for examining JavaScript code to identify website encryption, request signatures, and anti-bot checks, then documenting the findings in Python.

soulcodex/agentic

Skill Claude CodeCodex

Guides manual dependency injection wiring for Go services: three-tier naming taxonomy (Provide/MustProvide/Must), Must-pattern entrypoints, OS-signal-driven context lifecycle, common provider structs, infrastructure must-builders, interface-segregated bus registration, decorator/tracing wrappers, and…

sergekostenchuk/xray-xhttp-vpn-orchestrator

Skill Claude CodeCodex

Coordinate the local Xray/VLESS/XHTTP VPN workflow, route tasks to internal worker modules, enforce scoped alarms, and accept outputs only after evidence and review.

goldk3y/mastra-system-check

Skill Claude CodeCodex

Comprehensive system check for Mastra AI agent projects. Validates configuration, agents, workflows, memory, tools, prompts, and security across 66 rules organized by priority. Use when setting up new projects, debugging issues, reviewing code, or preparing for production deployment.

Zouhair-Boulahlib/Claude-Code-Etymologiae

Agent Claude Code

Reviews code for bugs, security issues, and style problems.

brighton-labs/railguard-framework

Cursor rule Cursor

Briefly describe the purpose of this rule – Insert brief description of the secure behavior or threat mitigated.

skills-il/security-compliance

Skill Claude CodeCodex

Not legal advice and not a compliance opinion. Israeli cybersecurity regulatory framework guidance covering INCD (Ma'arach HaSyber) national directives, Bank of Israel Directive 364, the consolidated IT, information security and cyber framework that took effect 18/05/2026 and repealed Directives 357, 361 and 363, plus…

smartchainark/skill-security-audit

Skill Claude CodeCodex

Detect malicious patterns in AI Agent skills — 13 detectors for backdoors, credential theft, data exfiltration, and supply-chain attacks. Based on SlowMist's ClawHub threat intelligence (472+ malicious skills). Pure Python, zero dependencies.