tractorjuice

Arckit.Agent Security

Name: Arckit.Agent Security
Author: tractorjuice

Security community

SOURCE https://github.com/tractorjuice/arckit-codex/blob/main/commands/arckit.agent-security.md

Description

--- 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 ```text $ARGUMENTS ``` ## Instructions > **Note**: Before generating, scan `projects/` for existing project directories. For each project, list all `ARC-*.md` artifacts,

Installation

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.