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.

Detecting prompt injections with Prompt Guard v1.0.0

Use this resource to detect prompt injection and jailbreak attempts in LLM inputs

New

  • 393 downloads
  • 243 likes
  • 246 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install prompt-injection-jailbreak-detection

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 guides you through installing the Prompt Guard classifier, checking a user message or third-party data, then filtering malicious content before it reaches your LLM. It also covers roleplay and embedded-command bypass cases.

Mostly picked by

Updated November 2, 2026

Card for the “Detecting prompt injections with Prompt Guard” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, prompt checking and user input filtering
  • SKILL.md: third-party data filtering, such as an API response or RAG content

Good fit for

  • You expose a chatbot to public users
  • Your RAG ingests web pages or untrusted documents

Not for

    Tags

    • security
    • prompt injection
    • jailbreak
    • llm

    About

    You say

    “Check with Prompt Guard whether this message tries to override my assistant's instructions.”

    Card for the “Detecting prompt injections with Prompt Guard” skill

    Skill published by Orchestra Research 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 detect prompt injection and jailbreak attempts in LLM inputs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md9.5 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/07-safety-alignment/prompt-guard
    Licence
    MIT

    Notice

    « prompt-guard » (Orchestra Research, 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.