Security · Model Context Protocol

Audit an Agent Skill, MCP server, connector, or desktop extension before installation by tracing code, dependencies, permissions, credentials, data flow, and irreversible actions.

sickn33/agentic-awesome-skills

Scan application source, agent skills, and MCP components; run penetration tests against scoped web test deployments, validate findings, and configure scan gates.

first-fluke/oh-my-agent

LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file…

hardw00t/ai-security-arsenal

Run Azure compliance and security audits with azqr plus Key Vault expiration checks.

microsoft/GitHub-Copilot-for-Azure

This skill should be used when developing SAP UI5 applications, including creating freestyle apps, Fiori Elements apps, custom controls, testing, data binding, OData integration, routing, and…

secondsky/sap-skills

Entry point for any development task in this repo — feature, bugfix, refactor, cleanup, a new command, target or evaluator, a collector change.

guardana/guardana

A skill your agent uses when you have a Foundry or Hardhat repository of Solidity or Vyper contracts and want the end-to-end EVM review workflow on native CLIs — a slither static pass, semgrep taint…

mtarcure/claude-vibe-squad

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10).

elementalsouls/Claude-BugHunter

Audit MCP (Model Context Protocol) server configurations for security issues.

github/awesome-copilot

Verter codebase architecture: high-level module map, TypeScript packages, plugin system, CSS analysis, MCP server, static analysis types

pikax/verter

Run osv-scanner via the mantisosvscanner MCP server for SCA (vulnerable dependency) findings

deonmenezes/mantishack

Composite Phase-2 audit worker (ADR-150). An agent skill from ruvnet/ruflo.

ruvnet/ruflo

Weekly supply-chain hygiene scan (Perplexity Bumblebee). An agent skill from Szotasz/marveen.

Szotasz/marveen

Security review of MCP (Model Context Protocol) server implementations and configurations.

OWASP/secure-agent-playbook

Run full security scans on the codebase using Ruflo security tools.

ruvnet/ruflo

Use before committing changes to auth, workspace scoping, channel webhooks, AI tools/MCP, permission settings, or anything handling untrusted channel content in ChatbotX.

ChatbotXIO/ChatbotX

Scan inputs for prompt injection, unsafe content, and adversarial attacks using AIDefence.

ruvnet/ruflo

Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions, rate limiting, input-schema…

github/awesome-copilot

A skill your agent uses when an open-source developer tool, package, CLI, agent, or MCP server must be evaluated for legitimacy, supply-chain risk, telemetry, dangerous capabilities, claim accuracy…

asimons81/hermes-field-kit

Capture a Burp Suite Repeater request/response as a PoC image (targets/<eng/poc/) by driving the Burp MCP + the Kali GUI.

Encod3d-Sec/TORCH

Create OPA governance policies for Harness via MCP. An agent skill from harness/harness-skills.

harness/harness-skills

AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning detection, model-output validation and…

modu-ai/moai-adk

Deep code property graph analysis with Joern CPG (AST+CFG+PDG) and CodeQL for control flow, data flow, taint analysis, and security auditing

alinaqi/maggy

Set up agent context for a project. An agent skill from unxed/f4.

unxed/f4

Run and inspect the local pieces of Guardana — the throwaway PostgreSQL for the collector, the collector itself, a fake OpenAI-compatible endpoint to probe, the documentation site served locally…

guardana/guardana

ANALYSIS SKILL — Azure compliance and security auditing: best practices, Key Vault expiration monitoring, resource validation.

jonathan-vella/apex

Find decision-makers at a specific company using Apollo, Crustdata, Fiber, and PDL people search via Gooseworks MCP.

gooseworks-ai/goose-skills

Run trufflehog via the mantistrufflehog MCP server and handle secret findings without ever exposing the raw secret

deonmenezes/mantishack

Behavioral trust grades (A–F) for MCP servers. An agent skill from BankrBot/skills.

BankrBot/skills

Enterprise-review-grade threat model from harness threat-model {path}.

ruvnet/ruflo

Explore GTI relationships for an IOC to discover related entities.

dandye/ai-runbooks

Drive Burp Suite over its MCP server as an AI triage + attack layer - review proxy history for signals, replay via Repeater/send, OOB-gate blind bugs with Collaborator, fuzz via Intruder (RoE-safe)…

Encod3d-Sec/TORCH

MCP server attack hunting - tool poisoning, indirect prompt injection via tool output, rug-pull updates, cross-tool shadowing, over-permissioned/excessive-agency tools, lethal trifecta.

Encod3d-Sec/TORCH

Search, query, and maintain the qmd-indexed wiki - semantic search, keyword search, re-index after adding pages, check index status.

Encod3d-Sec/TORCH

Periodic security sweep of Atlas in four areas (MCP and CLI, the Tauri desktop shell, the web renderer and connectors, the supply chain and CI) that follows untrusted input to what it can reach…

wlsdks/ontology-atlas

Defensive security engineering judgment, distilled from a stronger model - invoke when THREAT MODELING a system or feature; making security-relevant design decisions (auth, crypto, trust boundaries…

telagod/code-abyss

A skill your agent uses when closing a patch cycle with rigorous stress LAST on the Railway hub, bensbench x86 fieldbus → MQTTS, CSV/synth59/Creekside/gate 19, B100 Railway-only, light OWASP ZAP…

bbartling/open-fdd

Review an MCP server for common security gaps: LLM-facing surfaces as injection vector (tools, resources, prompts, descriptions), scope blast radius, destructive ops without consent, upstream auth…

cyanheads/pubmed-mcp-server

Audit MCP servers for tool poisoning, tool shadowing, rug pulls, SSRF, and unauthenticated exposure using Invariant Labs' mcp-scan for static/runtime scanning plus manual SSRF/auth checks and…

mukul975/Anthropic-Cybersecurity-Skills

Inspect Check Point security policies, threat intelligence, gateways, and SASE through its MCP integrations.

automateyournetwork/netclaw

Systematic diagnosis of a red test, a rule that fires or stays silent wrongly, a scan or probe whose artifact looks wrong, a collector error, a red CI run or a gate that is green for the wrong reason.

guardana/guardana

Audit MCP (Model Context Protocol) server configurations for security issues.

boshi-xixixi/TraeSkill

Read-only audit of MCP definition language across an existing surface — tools, resources, prompts, server instructions.

cyanheads/pubmed-mcp-server

Run semgrep via the mantissemgrep MCP server and triage results into the candidate/confirmed/rejected lifecycle

deonmenezes/mantishack

MCP gateway security patterns, token management, request validation, and audit logging for MCP communications

Hack23/cia

Manage Google Security Operations (SecOps) SOAR cases throughout their lifecycle.

google/skills

Diagnose and operate Spring AI projects with version-aware Maven or Gradle checks for ChatClient, advisors, retrieval, conversation memory, tool/MCP boundaries, streaming, configuration, and…

magnus919/agent-skills

使用 AgentShield 扫描 Claude Code 配置（.claude/ 目录）中的安全漏洞、配置错误和注入风险。检查 CLAUDE.md、settings.json、MCP 服务端、钩子（Hooks）和智能体（Agents）定义。

xu-xiang/everything-claude-code-zh