17,271 tagged Security, measured the same way as everything else here.
Browse within: cybersecurity 468bug-bounty 248agent 224generative-ai 178LangChain 176hacking 175skills 116autonomous-pentesting 115claude-ai 112cloud-security 112redteam 104LLM 103cors-exploitation 79firebase-hacking 78
actions-marketplace-validations/caglarbozkurt_mcp-heimdall
Skill Claude CodeCodex
Vet a Model Context Protocol (MCP) server for safety before installing or connecting it. Use when the user wants to check, audit, scan, or review an MCP server for prompt-injection, data-exfiltration, or malicious capabilities — given a directory, npm package, GitHub repo, or a tools/list JSON dump.
threadlinqs-cmd/intelthreadlinqs-mcp
Skill Claude CodeCodex
Operate the Threadlinqs Intelligence MCP server — 73 threat-intelligence tools covering threats, detection rules in Splunk SPL / Microsoft KQL / Sigma, IOCs, threat actors, CVE/CWE enrichment, MITRE ATT&CK coverage and prediction, C2 infrastructure, the correlation graph, and STIX 2.1 / ATT&CK Navigator export. Use…
Skill Claude CodeCodex
Scan a public GitHub MCP-server repository for security issues before installing or connecting to it. Calls the hosted compuute-scan API at scan.compuute.se and returns severity counts, a 0-100 score, the most severe findings, and an honest triage disclaimer. Use BEFORE recommending or installing an unfamiliar MCP…
Skill Claude CodeCodex
Use this skill when the user is building, securing, or auditing a browser-based AI agent (Playwright, Puppeteer, Stagehand, browser-use, or custom browser automation). Triggers on requests to "secure my browser agent", "detect prompt injection in web pages", "block my agent from visiting bad URLs", "scan this page for…
coti-io/coti-sdk-private-messaging
Skill Claude CodeCodex
Send and receive private encrypted messages between AI agents for private agent-to-agent messaging, encrypted communication between autonomous agents, hidden state exchange, confidential multi-agent workflow coordination, delegation, expert review, plan synchronization, negotiation, inbox processing, and sharing…
Skill Claude CodeCodex
MCP server exposing cryptography library functionality including encryption, hashing, and key derivation.
Skill Claude CodeCodex
MCP server that exposes Capstone disassembly framework functionality for binary disassembly, reverse engineering, and instruction analysis.
Skill Claude CodeCodex
MCP server for ECDSA cryptography operations.
Skill Claude CodeCodex
MCP server exposing hashlib functionality.
Skill Claude CodeCodex
Prove your agent is an authorized actor, not a bot. MCP-native identity declaration for agent commerce.
chainguard-dev/chainguard-cursor-plugin
Skill Claude CodeCodex
Check CVEs and security advisories for a Chainguard image or APK package. Use when the user asks about vulnerabilities, CVEs, or the security status of an image.
sonatype/sonatype-cursor-plugin
Skill Claude CodeCodex
Comprehensive security audit of all project dependencies. Scans package manifests and reports vulnerabilities, license issues, and quality concerns prioritized by severity.
Skill Claude CodeCodex
You are operating with Carapace, a security and alignment layer that monitors your actions, verifies sensitive operations, and keeps you anchored to the user's goals.
Skill Claude CodeCodex
This skill teaches Claude how to use the parental-control MCP server in agent sessions.
Agent-Sovereignty-Initiative/ASP-MCP-Server
Skill Claude CodeCodex
An agent-skill protection tool that uses the ASP protocol to protect skills during collaboration.
ceweldy/bitwarden-agent-vault-mcp
Skill Codex
Mandatory persistent credential workflow backed by Bitwarden Secrets Manager. Use implicitly whenever Codex creates, generates, receives, discovers, needs, stores, retrieves, updates, rotates, shares, or uses a password, API key, access token, client secret, deployment credential, or other stable secret; before asking…
Skill Claude CodeCodex
List connector types and bindings before executing an action. Use connectorsrun with a stored binding. Do not request or expose raw secrets. A delegated grant can limit one exact binding and action, and cannot exceed the receiving agent's standing capabilities.
Skill Claude CodeCodex
Como a autenticação Cognito do MCP Guedder liga e o que cada env var faz. Use ao configurar deploy autenticado, depurar 401 no MCP, ou decidir entre modo público e modo com token.
Skill Claude CodeCodex
Inspect and fix email authentication (SPF, DKIM, DMARC, MTA-STS, BIMI) with Palisade. When to use: a domain's mail is being rejected or spoofed, a DMARC record needs writing or moving to p=reject, DMARC reports need reading, or an IT team or MSP wants ongoing monitoring across many domains. Not for sending or…
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: