xone-ai-incident-lab 0.2.1

Safe local incident simulations for AI agents, MCP tools, and agent-generated code.

ai-incident-lab

Languages: English | 中文

Runnable incident simulations for AI agents, MCP tools, and agent-generated code.

Status

v0.2.1 - safe-local scenario CLI, bundled scenario pack, and first-run init flow.

Purpose

Create safe local workshops and regression scenarios that make Safe Agent Operations concrete.

First Production Surface

Local-only incident scenarios mapped to X-One tools, expected findings, cleanup steps, and reviewer lessons.

After PyPI publication:

python3 -m pip install xone-ai-incident-lab
ai-incident-lab init --output ai-incident-scenarios
ai-incident-lab list --scenarios ai-incident-scenarios
ai-incident-lab validate --scenarios ai-incident-scenarios
ai-incident-lab render --scenarios ai-incident-scenarios --format markdown --output ai-incident-runbook.md
ai-incident-lab render --scenarios ai-incident-scenarios --format json --output ai-incident-runbook.json

After Homebrew tap update:

brew install x-one-ai/tap/ai-incident-lab
ai-incident-lab --version

For local development:

python3 -m pip install -e '.[dev]'
python3 -m pytest tests -q
ai-incident-lab validate --scenarios scenarios

Required Evidence

• scenario README
• safe reproduction steps
• expected finding mapping
• cleanup instructions
• teaching notes

Scenario Contract

Scenarios use ai-incident-lab.scenario.v1 and must remain safe-local. They are review exercises, not exploit kits or runtime protection.

Non-Goals

• no real exploit kit
• no hosted sandbox first
• no unsafe secret-bearing fixtures

OPT Operating Model

This project references the shared One Person Team workflow through ops/opt-overlay.md. Project-specific constraints live under ops/constraints, and evolvable local skills live under ops/skills.

Blocked Inputs

Inputs that require user or real-world data are recorded in ../x-one-skipped-inputs.md and should not block foundation work.

Docs

• Product Foundation
• Scenario Lab Design
• Publishing
• Homebrew Packaging
• OPT Overlay
• Production Constraints
• Main Entry Constraints
• Skill Evolution