Навыки: Безопасность

Add OAuth authentication to MCP servers on Cloudflare Workers. Uses @cloudflare/workers-oauth-provider with Google OAuth...

Evaluate the safety of an MCP server before connecting it to an AI agent. Covers outbound network requests, tool blast-r...

Multi-agent and MCP pipeline security with 5-layer defense architecture. Use when building MCP servers, multi-agent syst...

Detects MCP tool handlers vulnerable to malicious inputs, hardcoded secrets, or unrestricted file/shell access. Use when...

MCP security patterns for prompt injection defense, tool poisoning prevention, and permission management. Use when secur...

Use this skill when reviewing Model Context Protocol (MCP) servers, clients, connectors, tool manifests, hosted MCP depl...

Use when designing or reviewing MCP servers and MCP-exposed capabilities used by PonyBunny.

Design, audit, harden, review, or upgrade MCP servers and MCP Apps with revision-aware protocol profiles, explicit HTTP/...

Vet a third-party MCP server before it can run: install-card completeness (manifest, provenance, permission label, healt...

EU MDR 2017/745 compliance specialist for medical device classification, technical documentation, clinical evidence, and...

Use this skill when a driver is being screened for sleep apnea. Covers FMCSA Medical Review Board (MRB) recommendations,...

Prepare a factual media brief with message, evidence, spokesperson guidance, likely questions, sensitivities, and respon...

List Plane workspace or project members and their roles Arguments: [scope] [project].

Meme coin and token security audit — rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass), Solan...

Audit project and global memory for bloat, stale decisions, duplicates, contradictions, unsafe content, missing provenan...

Record durable project decisions with rationale, alternatives, assumptions, status, and revisit triggers. Load when the...

Delete, redact, or archive project and global memories when the user says forget this, delete memory, remove that prefer...

Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entri...

Promote project-specific memories into strict, small global memory only when they are cross-project, stable, useful, saf...

Produce share-safe copies of memory files under /tmp with PII redacted (paths, emails, session IDs, dates) and credentia...

Mend integration. Manage data, records, and automate workflows. Use when the user wants to interact with Mend data.

Receive and verify Cisco Meraki Dashboard webhook alerts. Use when setting up Meraki webhook handlers, validating the sh...

Consolidate multiple Git worktrees and clones of a repository into a single clean checkout, safely merge associated PRs...

Translates Mermaid sequenceDiagrams describing cryptographic protocols into ProVerif formal verification models (.pv fil...

Security policy for MERN apps. Enforces OWASP Top 10 and CWE Top 25 mitigations.

Analyze Istio, Consul, and Linkerd service mesh configurations for security vulnerabilities with NIST 800-53 control map...

Secure NATS, RabbitMQ, Kafka, and similar message buses against misconfiguration and cross-tenant leakage. Covers accoun...

Appa's messenger hawk for PR feedback. Hawky, Sokka's messenger hawk, flies out and brings the letters home. Use for get...

Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutat...

meta-business-posting — Publish posts to a Facebook Page through the agent's own logged-in browser session or the Meta G...

Sets up the Meta pixel and its conversions from nothing - base install mechanism, standard events mapped to the funnel w...

Looks harmless but omits important runtime requirements.

This skill should be used when the user asks to "use Metasploit for penetration testing", "exploit vulnerabilities with...

⚠️ AUTHORIZED USE ONLY > This skill is for educational purposes or authorized security assessments only. > You must have...

This skill should be used when the user asks to "use Metasploit for penetration testing", "exploit vulnerabilities with...

> The Metasploit Framework is the world's most widely used penetration testing platform, maintained by Rapid7. It cont...

Comprehensive audit methodology guides covering the full security auditor workflow -- from preparation and AI-assisted a...

MEV protection against sandwich attacks and front-running

Obtenir et gérer un access token pour l'API Merci Facteur (envoi de courrier papier, recommandé, recommandé électronique...

Talk to My First Million Hosts about their expertise. My First Million Hosts provides authentic advice using their menta...

The M365 tenant security checks that distinguish a secure tenant from a vulnerable one: per-user authentication-method i...

The Entra ID user object as M365's central identity: key properties and their MSP relevance, account status values, the...

Draft, rewrite, or audit friendly, concise product and technical UX content using an independently expressed reference-o...

Methodology for detecting client SOC patches, attacker activity, and security-state changes that occur DURING a red-team...

Route protection and authorization patterns for Clerk middleware. Use when implementing route guards, protecting API rou...

Identify security risks, vulnerabilities, and unsafe patterns in code and configuration.

Audit a codebase or directory for deletion candidates: dead code, unused dependencies, single-use abstractions, config t...

Explain minimalist: what it does, the levels, the commands, the guardrail. Use when the user says "minimalist help" or a...