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 defense v1.0.0

Use this resource to protect an LLM application against prompt injection

New

  • 310 downloads
  • 205 likes
  • 212 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install prompt-injection-defense-llm

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 helps you protect an LLM application against direct and indirect injections and jailbreaks: separating instructions from data, input sanitization and defense in depth. You get a defense architecture and the controls to test.

Mostly picked by

Updated November 2, 2026

Card for the “Prompt injection defense” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: LLM security researcher role
  • references/patterns.md: injection defense models
  • references/sharp_edges.md: known weaknesses and their causes

Good fit for

  • Your assistant reads documents or web pages that may hide instructions
  • You open an agent to users who might try to hijack it

Not for

    Tags

    • prompt injection
    • security
    • llm
    • jailbreak

    About

    You say

    “Protect my support chatbot, which reads customer emails, against hidden instructions in messages.”

    Card for the “Prompt injection defense” skill

    Skill published by omer-metin under the Apache-2.0 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 protect an LLM application against prompt injection
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/patterns.md19.7 KB
    • references/sharp_edges.md20.7 KB
    • references/validations.md4.9 KB
    • SKILL.md1.9 KB

    Origin and licence

    Listed unmodified

    Author
    omer-metin
    Source
    github.com/omer-metin/skills-for-antigravity/tree/e8dcf4e8737921a10088bd5c9eb65e81f74c051f/skills/prompt-injection-defense
    Licence
    Apache-2.0

    Notice

    « prompt-injection-defense » (omer-metin, Apache-2.0) 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.