# microsoft/AI-Red-Teaming-Playground-Labs

AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.

Repository: https://github.com/microsoft/AI-Red-Teaming-Playground-Labs
Canonical: https://ross.abutalabs.com/products/ai-red-teaming-playground-labs
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai-red-team, ai-red-teaming, prompt-injection
Last push: 2026-02-13T14:19:16+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 35, longevity 34
- inputs: {"age_days": 483, "days_push": 201, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2049, forks 307 (observed 2026-08-28T04:06:09.065870+00:00)

## What it is
A set of hands-on AI red teaming playground labs from Microsoft, built on a modified Chat Copilot, used to teach adversarial attacks on AI systems such as prompt injection and metaprompt extraction. It includes challenge infrastructure, scoring, and PyRIT notebooks for automated attack demonstrations.

## Use cases
- learn ai red teaming hands-on
- practice prompt injection attacks against an llm chatbot
- run ai security training labs for a team
- automate llm attack challenges with pyrit
- extract system prompts and secrets from a chatbot
- teach adversarial machine learning and responsible ai failures

## When to choose
- you want structured, self-hosted labs to learn or teach AI red teaming
- you need realistic vulnerable AI targets for prompt injection practice
- you want to pair manual attacks with PyRIT automation notebooks

## When to avoid
- you need a production-ready secure chatbot rather than a deliberately vulnerable training target
- you want a general-purpose AI security scanning tool rather than training challenges
- you cannot run the required Docker-based lab infrastructure

## Facets
- artifact type: learning-resource
- maturity: active
- function: security, penetration-testing, chatbot, developer-tools
- domain: artificial-intelligence, security, large-language-models, education, tutorials
- platform: self-hosted, python
- tags: ai-red-teaming, prompt-injection, pyrit, ctf-challenges, training-labs, chat-copilot, docker, web-server

## Member repositories
- microsoft/AI-Red-Teaming-Playground-Labs (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:09.065870+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:57:37.615635+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/AI-Red-Teaming-Playground-Labs (fetched 2026-08-28T04:06:09.065870+00:00, sha ab4cf947aff2)
- Data as of 2026-08-30T08:39:29.467469+00:00.