Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Deliberately vulnerable RAG chatbot for AI attack testing v1.0.0

Use this resource to demonstrate and test attacks against a RAG chatbot

New

  • 361 downloads
  • 202 likes
  • 240 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install rag-chatbot-attack-sandbox

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent installs the server, switches between secure and vulnerable modes, then runs the attack scenarios. You get a repeatable demonstration that works offline with the mock provider.

Mostly picked by

Updated November 2, 2026

Card for the “Deliberately vulnerable RAG chatbot for AI attack testing” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md : installation, .env file and launch
  • SKILL.md : provider choice (offline mock, OpenAI, Claude, Gemini)

Good fit for

  • You train a team on the risks of RAG applications
  • You want to test a defense before applying it to your own chatbot

Not for

    Tags

    • rag
    • prompt injection
    • owasp llm
    • demo

    About

    You say

    “Launch the RAG demo in vulnerable mode and show me the indirect injection.”

    Card for the “Deliberately vulnerable RAG chatbot for AI attack testing” skill

    Skill published by reason-machines under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to demonstrate and test attacks against a RAG chatbot
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE0 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md18.2 KB

    Origin and licence

    Listed unmodified

    Author
    reason-machines
    Source
    github.com/reason-machines/security-skills/tree/1722e18788818fff1b0144132437936c2095971c/skills/ai-runtime-security-sandbox
    Licence
    MIT

    Notice

    « ai-runtime-security-sandbox » (reason-machines, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.