Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

Claude Code running in sandbox. Packed as single portable executable with no dependency. Has better performance than official version.

Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and risky agent actions.

Security audit tool for Claude Desktop and Claude Code on macOS — single-command visibility into MCP servers, extensions, plugins, connectors, scheduled tasks, and permissions.

AI-powered security assessment SKILLS for your codebase. Multi-language (JS, Go, Python, Rust, Java, PHP, Ruby, C#). Works with Claude Code, Codex, OpenCode, etc.

credit score for context

Jibril: A performant and low impact Linux runtime security tool agent.

Security skills for AI coding agents — incident response for supply chain attacks, credential rotation, IOC detection. Works with Claude Code, Codex, Cursor, or as standalone scripts and runbooks.

Detect shadow AI threats running in your org's machines via MDM

Automated threat modeling toolkit — STRIDE + AI-specific threats in one command

NFTBan is an open-source Linux Intrusion Prevention System (IPS) and firewall manager built on nftables, designed to integrate cleanly with modern Linux security stacks.

A hardened, isolated development environment for VS Code with GitHub Copilot.

Claude Code plugin — 18 cybersecurity domains: IR, DFIR, DevSecOps, SOC, Code Security, Container, Compliance, Cloud/CSPM, Zero Trust, AI/ML, API, Vulnerability Mgmt, Threat Intel, OT/ICS, Governance. Bilingual Thai+English.

🤖 Enhance AI coding assistants with battle-tested rules for reliability, predictability, and effectiveness in your projects.

Fork of PaloAltoNetworks/prisma-airs-integrations — setup guides for Anthropic, Kong, LiteLLM, n8n, Portkey, and TrueFoundry

Demo AI chat app with optional Prisma AIRS Runtime Security for before/after red team testing comparison

Minimal AI chat application for testing Prisma AIRS Red Teaming - provides baseline vulnerability assessment without building your own AI application

Simple shell script for automated domain recognition with some tools

AI-assisted black-box security audit as a Claude Code skill. Orchestrates 25+ security tools with LLM reasoning to find business logic vulnerabilities that scanners miss.

Operational Engine for Managing and Auditing Private AI Agents with OpenClaw and Arize Phoenix.