26,946 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
Detect Server-Side Template Injection (SSTI) vulnerabilities in a codebase using a three-phase approach: recon (find template rendering sites that use dynamic strings), batched verify (trace user input to those sites in parallel subagents, 3 candidates each), and merge (consolidate batch results). Requires…
Cursor rule Cursor ✓ vendor
Non-negotiable safety and scope constraints for Box MCP tool usage.
Plugin Claude Code
Bundles 2 commands · 27 tokens together
A collection of Claude Code plugins developed by PagerDuty for pre-commit risk assessment and PagerDuty skill creation for AI agents (Early Access).
Plugin Claude Code
Bundles 1 skill, 3 commands · 108 tokens together
Static technical-debt analysis across 14 languages, exposed as MCP tools and resources (SQALE ratings, debt summaries, custom rules, dependency vulnerabilities).
Skill Claude CodeCodex
Evidence-driven application audit protocol for security, authorization, privacy, concurrency, state integrity, reliability, performance, accessibility, visual consistency, responsive behavior, and release readiness. Use for incremental checks, pre-merge review, pre-launch audits, high-stakes deep audits, AI-generated…
antgroup/adversarial-ai-coding-plugin
Plugin Claude Code
Bundles 5 skills, 2 hooks · 706 tokens together
A coding plugin built around adversarial review, where opposing checks look for security problems in generated code.
Plugin Claude Code
Bundles 1 skill, 1 command, 2 hooks · 0 tokens together
A dependency security plugin for Claude Code. DepGuard intercepts package installs, checks reputation with Socket.dev, runs installs in a Modal sandbox, and blocks suspicious behavior before it reaches your machine.
Command Claude Code
Complete authentication system with JWT tokens, OAuth2, and role-based access control.
Cursor rule Cursor
Reviews Python code for unguarded AI agent tool calls. Use when reviewing agent code, scanning for security issues, or checking tool call safety.
Plugin Claude Code
Bundles 8 skills, 11 hooks · 147 tokens together
Security enforcement layer for Claude Code. Blocks dangerous commands, audits every tool call, detects prompt injection.
Plugin Claude Code
Bundles 1 skill, 1 hook · 50 tokens together
Supply-chain security guard that intercepts package install commands across npm, pnpm, pip, go, and cargo ecosystems and enforces package risk policies before execution.
Skill Claude CodeCodex
Audytuje bezpieczeństwo skilla, pluginu lub agenta Claude Code przed instalacją. Warstwa statyczna (heurystyki) plus subagent-audytor tylko do odczytu wykrywają prompt injection, kradzież sekretów, exfiltrację danych, obfuskację i persistence. Pozyskuje kod do izolowanego katalogu tymczasowego, nigdy bezpośrednio do…
godlovepenn/attack-simulation-claude
Plugin Claude Code
Bundles 6 skills, 8 commands, 5 agents · 786 tokens together
Automate TTPForge TTP creation, validation, and management for adversary simulation.
skjortan23/aws-security-mcp-server
MCP server Claude CodeCodexCursor +2
MCP server "aws-security-mcp-server" as configured in skjortan23/aws-security-mcp-server. Runs locally from the aws-security-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
An MCP server to interact with a the NVD Database API. Runs locally from the mcp-nvd Python package.
MCP server Claude CodeCodexCursor +2
SquatGuard MCP Template for Python. Runs locally from the mcp-pentest npm package.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-exploitdb" as configured in CyberRoute/mcpexploitdb. Runs locally from the mcp-exploitdb Python package.
MCP server Claude CodeCodexCursor +2
A local Node.js MCP server for security audits of frontend projects. It checks dependencies, which are external software packages a project relies on, in local projects and remote repositories.
MCP server Claude CodeCodexCursor +2
MCP server "safebreach-mcp-server" as configured in SafeBreach/safebreach-mcp. Runs locally from the safebreach-mcp-server Python package.
Skill Claude CodeCodex
Manage Discord channel access for cursor-discord-channels — pairing, allowlists, trustedBots. Use when configuring the bridge or when the user asks about Discord bot access.
MCP server Claude CodeCodexCursor +2
A Model Context Protocol server used to integrate Okta resources and Claude Desktop. Runs locally from the @yiyang.1i/okta-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Reliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail. Runs locally from the mcp-bastion npm package.
Skill Claude Code
Discover the best Claude Code extensions on the web AND tell the user how safe each one is before installing. Reads the user's Claude Code setup (project context, memory, history), asks a few questions to understand their goal (general or a specific idea), then surfaces a ranked shortlist - name, what it does, what…
Skill Claude CodeCodex
Elite manual security code review skill for deep, adversarial vulnerability hunting and exploit-chain discovery. Trigger when the user asks to: "do a deep security audit", "manual code review", "find exploit chains", "hunt for logic bugs", "red-team this codebase", "do an offensive security review", "review this like…
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: