24,655 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.
brighton-labs/railguard-cursor-coding
Cursor rule Cursor
Enforces secure database access in C# applications using the full RAILGUARD framework. Covers safe use of ADO.NET, Entity Framework Core, parameterized queries, credential management, and logging hygiene.
Plugin Claude Code
Plugin marketplace listing 1 plugin: secure-sdlc-agents.
Skill Claude CodeCodex
Authorized penetration tester persona — offensive security specialist for network, web app, cloud, and Active Directory assessments. Requires explicit authorization.
MCP server Claude CodeCodexCursor +2
Website & Server Diagnostics MCP Server. DNS, SSL, HTTP headers, security scan, performance audit. Runs locally from the mcp-diagnostics npm package.
MCP server Claude CodeCodexCursor +2
MCP server "sb-siem-mcp" as configured in Sbharadwaj05/sb-siem-mcp. Runs locally from the sb-siem-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for the CrowdStrike Falcon platform. Runs locally from the crowdstrike-mcp Python package.
2233admin/reverse-skill-evolver
Skill Claude CodeCodex
A security-testing skill that plans multi-stage attack paths and coordinates specialized security tasks. It covers scenarios such as moving from an external foothold toward internal systems, but is not needed for single tasks like port scanning.
Skill Claude Code
Route API calls through the Aegis credential proxy — keeps raw API keys out of the agent context.
Plugin Claude Code
Bundles 1 skill · 116 tokens together
AI-driven intercepting proxy + rootless execution sandbox for web pentesting. Installs the burpwn skill, which teaches the agent to create a session and route target-facing network commands through burpwn exec so their traffic is captured, MITM-decrypted, searchable, replayable, and live-interceptable. Requires the.
MCP server Claude CodeCodexCursor +2
MCP server for MITRE ATT&CK framework. Runs locally from the mitre-mcp Python package.
Skill Claude CodeCodex
CVE-oriented multi-agent code audit system. Use when user provides a git repository URL for vulnerability discovery with the goal of submitting CVEs. This skill orchestrates subagents to find exploitable vulnerabilities (RCE, SQLi, Auth Bypass, etc.), write weaponized POCs, and generate CVE-ready reports. ALWAYS use…
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Attack patterns and real-world examples sourced from the HackerBot Claw campaign analysis by StepSecurity (2025): https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation -->.
Skill Claude CodeCodex
Turnkey cybersecurity lab — 2,077 skills, 131+ tools, 28 frameworks, and evolving methodology for security research, pentesting, forensics, and threat intelligence. Includes one-step ecosystem cloner for 8 repositories.
yanglittlecat/blackbox-pentest
Skill Claude CodeCodex
A set of rules for carrying out authorized black-box penetration tests, where the tester examines a system without access to its source code. It defines testing boundaries, safety limits, and the evidence needed to report a vulnerability.
Skill Claude CodeCodex
A toolkit for taking software apart to inspect how it works, across formats such as Android packages, Windows programs, Linux binaries, JavaScript, and firmware.
Skill Claude CodeCodex
Manage 1Password Developer Environments via the bundled MCP server. Use when creating, importing, or mounting .env files; listing Environment variable names; adding or updating Environment variables; renaming environments; or calling any 1Password MCP tool. On macOS/Linux, import-from-.env includes createlocalenvfile…
codefrog7426-gzkos/responsible-disclosure
Skill Claude CodeCodex
Draft a responsible vulnerability disclosure policy for SaaS/devtools: scope, safe harbor posture, channels, timelines, and what not to do — no exploit detail. Triggers: responsible disclosure policy, vulnerability disclosure policy VDP, security.txt companion policy, report vulnerability page, coordinated disclosure.…
Skill Claude Code needs its repo
A browser-driven helper for opening permission scopes for an existing Feishu bot app. Feishu is a workplace collaboration platform, and permission scopes control what a bot can read or do.
Plugin Claude Code
Bundles 1 skill, 5 hooks, 1 MCP server · 129 tokens together
Semgrep Guardian: Scans agent-generated code for security vulnerabilities.
Skill Claude Code
An image-safety review skill that compresses local images and sends them to an API to check for sexual, political, and violent content.
Agent Claude Code
Reviews pull requests for security vulnerabilities, logic bugs, data loss risks, and API misuse. Runs project linters and type checkers to verify findings before commenting. Specialized for the Symbiosis codebase (Python stdlib-only Claude Code plugins).
Cursor rule Cursor
Scan Solidity contracts for Uniswap CCA vulnerabilities — core bugs and integration footguns. Invoke by asking "scan for CCA vulnerabilities" or "run CCA audit".
MCP server Claude CodeCodexCursor +2
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval. Remote server at mcp.tap.human.tech.
Cursor rule Cursor
Security best practices for LLM/AI applications - prompt injection defense, rate limiting, PII protection.
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: