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.

Prompt injection tests for AI apps v1.0.0

Use this resource to test an LLM application's defenses against prompt injection

New

  • 508 downloads
  • 117 likes
  • 196 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install prompt-injection-red-team

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 finds the entry points where untrusted content reaches the model (direct input, files, web pages, tool results), then runs the thirteen attack intents of the Arcanum taxonomy (CC BY 4.0). You get the scenarios tested, the tests that succeeded and the defenses to strengthen.

Mostly picked by

Updated November 2, 2026

Card for the “Prompt injection tests for AI apps” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
CC-BY-4.0

Similar resources

View all

What you get

  • SKILL.md: mapping of direct and indirect inputs
  • SKILL.md: tests per attack intent and output format

Good fit for

  • Your application sends external documents or web pages to the LLM
  • You want to validate guardrails before a production release

Not for

    Tags

    • prompt injection
    • llm
    • red team

    About

    You say

    “Test our support chatbot's defenses against indirect prompt injection through customer documents.”

    Card for the “Prompt injection tests for AI apps” skill

    Skill published by owasp under the CC-BY-4.0 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 test an LLM application's defenses against prompt injection
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE0.2 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md3 KB

    Origin and licence

    Listed unmodified

    Author
    owasp
    Source
    github.com/owasp/secure-agent-playbook/tree/65d4efd2cd0b081d52101e9708792b944e4ddebb/plugins/ai-security-skills/skills/prompt-injection-test
    Licence
    CC-BY-4.0

    Notice

    « prompt-injection-test » (owasp, CC-BY-4.0) 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.