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 for LLM apps v1.0.0

Use this resource to protect an LLM application against prompt injection

New

  • 474 downloads
  • 210 likes
  • 181 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install prompt-injection-defenses

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 reviews the attack surface (chat, RAG, agents) and proposes layered defenses: input sanitization, canary tokens, output validation and tool permissions. You get Python functions and a defense configuration file.

Mostly picked by

Updated November 2, 2026

Card for the “Prompt injection defense for LLM apps” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: attack surface, defense in depth and input sanitization functions
  • SKILL.md: canary tokens, leakage checks and multi-layer configuration (prompt-defense-config.yaml)

Good fit for

  • Your LLM app reads untrusted documents or web pages
  • An agent with tools has been reported as vulnerable to injection

Not for

    Tags

    • prompt injection
    • llm
    • security
    • agents
    • rag

    About

    You say

    “Secure our RAG assistant that reads customer PDFs against prompt injection.”

    Card for the “Prompt injection defense for LLM apps” skill

    Skill published by bagelhole 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 protect an LLM application against prompt injection
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md15.9 KB

    Origin and licence

    Listed unmodified

    Author
    bagelhole
    Source
    github.com/bagelhole/devops-security-agent-skills/tree/0365f57a079b1332f95cf26e31dd2d5332a8399f/security/ai/prompt-injection-defense
    Licence
    MIT

    Notice

    « prompt-injection-defense » (bagelhole, 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.