ATLAS GATE MCP
"Enterprise MCP Security Gateway with MCP-Only Sandbox Enforcement"
2,832 个安全任务的工具和技能
"Enterprise MCP Security Gateway with MCP-Only Sandbox Enforcement"
Cold-start codebase audit skill for Claude Code
Claude Code skill for comprehensive security audits on SaaS web applications
Open-source MCP server + Claude Code skill that gives Claude the ability to autonomously explore any macOS application, analyze its user experience, map its full feature scope, and produce a rich human-readable audit report.
AI-Powered Bug Bounty Hunting Framework — Automated recon, vulnerability triage, exploit chain building, and report generation across HackerOne, Bugcrowd, Intigriti & Immunefi
Ethical Red Team & Bug Bounty Skill for AI agents - Authorized security testing with recon, scanning, analysis and OWASP/NIST compliant reporting
Security playbook for building, auditing, and repairing AI-generated or "vibe coded" systems. Use when reviewing vibe-coded apps, writing security-first prompts, hardening Supabase/RLS/API flows, designing pentest checklists, or repairing vulnerabilities such as race conditions, IDOR, user enumeration, upload validation flaws, secrets exposure, and business-logic abuse.
turn Mullvad into authenticated SOCKS5, HTTP, and HTTPS proxies.
Nightly librarian intelligence cycle: ingest last 24h of records, cluster patterns/failures, generate doctrine candidates, run hygiene audit, re-rank active doctrine, build next-day guidance packet, write scorecard, and queue promotion candidates.
Full writing audit — AI pattern removal, humanization, grammar, and platform-native styling
Azure DevOps skill for AI coding assistants — manage projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, and more (99 tools, 13 domains)
Per-agent scoped credential vault with JIT tokens, proxy enforcement, revocation, and audit logging for AI agents.
"CVE vulnerability fixing workflow for Debian packages. Searches CVE databases, generates patches with one-CVE-per-patch enforcement, validates with quilt (or git apply fallback), and submits to Gerrit/GitHub. Works without quilt/devscripts using fallback methods. Use when fixing CVEs in Debian packages, applying security patches, or managing Debian security updates."
🧪 Production-ready Newman (Postman CLI) skill for automated API testing with gold-standard security practices
>
Pentagon-grade red team security scanning for Claude Code. 19 agents, two tiers, zero gaps.
OpenClaw skill: audit and configure OpenClaw setup (models, auth, config)
OpenClaw skill: audit and repair Linux/macOS hosts running OpenClaw
Supply chain security scanner for any GitHub project. Single binary, zero config.
A Claude Code skill that assesses readiness before starting new features. Security-first evaluation of community skills/plugins. Complements Superpowers.
Claude Code skill to help audit/prevent bugs in Solana Anchor smart contracts
Security scanning skill for AI coding agents. CVE vulnerability detection, OWASP Top 10 code analysis, and dependency audits. Follows agentskills.io specification.
Comprehensive security analysis for gitignore patterns, env files, API key leakage, MCP leakage, LLM leakage, memory leakage, privacy violations, and security flaws
>
Reads your codebase and writes a CLAUDE.md file with build commands, architecture notes, and gotchas. Supports create, update, and audit modes with A-F quality scoring.
OpenClaw Security Sentinel
Security scanner for OpenClaw skills. Detects prompt injection, data exfiltration, and malicious code before installation.
"Use when: making HTTP requests to the Gemini Web API Wrapper; sending messages to Gemini; managing chats, gems, models, or deep research via REST API; streaming responses from Gemini; uploading files to Gemini; checking Gemini account status. This skill provides the complete API reference, authentication details, request/response formats, and usage patterns for the gemini-web-api-wrapper REST server."
Use when the user wants to connect to, test, or use the McDonalds MCP service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.
Cordyceps - The parasitic fungus that finds what's taking over your WordPress. Automated plugin vulnerability scanner powered by Mycelium + Patchstack Academy. OpenClaw skill.
Cairo and Starknet security skills for AI agents. 7 modules, 24 audits, 217 findings.
Full-stack security audit for Web, Mobile, Backend, IaC, Compliance, LLM/AI. OWASP Top 10:2025, MASVS v2, CIS Benchmarks, PCI-DSS, GDPR. CLI + Chrome MCP. Triggered by "security audit", "vulnerability scan", "pentest".
Deterministic workflow for AI security vulnerability scanning across code repos, dependency manifests, container images, infrastructure-as-code, CI/CD configs, and LLM applications. Use when asked to run AI/LLM security reviews, triage vulnerabilities, map findings to OWASP LLM Top 10, assign remediation SLAs, and produce evidence-ready audit artifacts.
Audit trail export & verification for compliance
Skill from gandli/openclaw-security-validation
An interactive cybersecurity education platform — a Single-Page Application where users learn security concepts through Theory, Demo, Lab, Quiz for every lesson.
Security scanning tool for OpenClaw Skills. Detects malicious code patterns and checks threat intelligence.
Honest, evidence-traceable peer-review skill for Claude Code users. Rule-based 8-dim scoring + LLM peer review + HTML dashboard. Self-audit and HR-portfolio modes.
Automatically refresh Canvas LMS API tokens via institutional IDP (CAS/SAML) login with RSA encryption
Token Janitor — OpenClaw skill to audit token waste
800 curated Claude Code skills — engineering, Azure SDK, testing, security, product, ML, and more. Zero paid-service dependencies.
Claude Code skill — systematic code quality audit based on NASA/JPL's Power of Ten rules
aws-security-detection
ClawGuard security assistant skill for OpenClaw. Reads scan reports, explains findings, analyzes fix impact, and guides remediation.
Claude Code skill for comprehensive security audits on SaaS web applications
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Since 2011, IPBan is the worlds most trusted, free security software to block hackers and botnets. With both Windows and Linux support, IPBan has your dedicated or cloud server protected. Upgrade to IPBan Pro today and get a discount. Learn more at ↓
Open source alternative to Semrush and Ahrefs