tractorjuice

Arckit.Agent Security — Security skill for Claude Code

Security community

Design AI agent security — sandboxing, permissions, injection defences, output validation.

How to install Arckit.Agent Security

Installs to ~/.claude/skills/tractorjuice-arckit-codex-arckit.agent-security/SKILL.md

Terminal
mkdir -p ~/.claude/skills/tractorjuice-arckit-codex-arckit.agent-security && curl -fsSL https://raw.githubusercontent.com/tractorjuice/arckit-codex/HEAD/commands/arckit.agent-security.md -o ~/.claude/skills/tractorjuice-arckit-codex-arckit.agent-security/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Arckit.Agent Security does

description: "Design AI agent security — sandboxing, permissions, injection defences, output validation"

You are helping an enterprise architect design an AI agent security architecture that establishes sandboxing, permissions, injection defences, and output validation for autonomous AI agent systems.

User Input

$ARGUMENTS

Instructions

**Note**: Before generating, scan `projects/` for existing project directories. For each project, list all `ARC-*.md` artifacts,

Alternatives in Security

  • FastAPI Review — Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu 243.5k ★
  • Security Guidance — Hook that warns about command injection, XSS, and unsafe patterns 14k ★
  • Security Guardian — Comprehensive security analysis for RTK CLI tool, focusing on command injection, shell escaping, hook security 11.9k ★

Full documentation available on GitHub

View Source Repository

Related Skills

Trail Of Bits Claude-code-config — Security skill for Claude Code

Trail Of Bits Claude-code-config

Opinionated production defaults from a top security firm: sandboxing, permissions, hooks, skills, MCP server c

Security community
Claude Code Security Setup — Security skill for Claude Code

Claude Code Security Setup

A secure Claude Code setup from Trail of Bits that provides opinionated defaults, documentation, and workflows

Security community
Collomia — Security skill for Claude Code

Collomia

Collomia is a provider-neutral agentic coding agent for the terminal. Every model-proposed action passes throu

Security community
Arckit.Agent Maturity — Security skill for Claude Code

Arckit.Agent Maturity

Assess AI agent program maturity across design, governance, security, integration, and operations

Security community
Arckit.Agent Governance — Security skill for Claude Code

Arckit.Agent Governance

Design AI agent governance — oversight models, approval workflows, audit requirements, compliance mapping

Security community
J Config Audit — Security skill for Claude Code

J Config Audit

Security audit of Claude, Codex, Gemini, and shared agent configuration for secrets, over-broad permissions, a

Security community

Related Agents

Gitnexus Security Boundary Reviewer — Security agent for Claude Code

Gitnexus Security Boundary Reviewer

GitNexus security and trust-boundary reviewer. Use for auth, permissions, secrets, injection, unsafe parsing,

Security community
Security Agent.Agent — Security agent for Claude Code

Security Agent.Agent

Use when a change touches permissions, authentication, dependencies, configuration, release surfaces, sensitiv

Security community
AI Security Reviewer — Security agent for Claude Code

AI Security Reviewer

Use this agent when reviewing AI-related code (prompts, agent loops, RAG systems, tool definitions, output han

Security community