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.

Defending AI agents against injection v1.0.0

Use this resource to secure an AI agent against injection, tool abuse and exfiltration

New

  • 571 downloads
  • 104 likes
  • 236 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install ai-agent-defense-controls

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 models threats with STRIDE, then designs controls: input validation, injection detection, sandboxed tool execution and server-side authorization. The examples are design sketches and are not a complete security boundary on their own.

Mostly picked by

Updated November 2, 2026

Card for the “Defending AI agents against injection” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: STRIDE threat model for agents
  • SKILL.md: input controls and sandboxed tool execution
  • references/details.md: technical details and configurations

Good fit for

  • Your agent calls tools that touch customer data
  • You add an agent that reads untrusted web pages or emails

Not for

    Tags

    • security
    • agents
    • injection
    • tools

    About

    You say

    “Assess the injection risks of my support agent and propose server-side controls.”

    Card for the “Defending AI agents against injection” skill

    Skill published by sickn33 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 secure an AI agent against injection, tool abuse and exfiltration
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/details.md32.8 KB
    • SKILL.md15.5 KB

    Origin and licence

    Listed unmodified

    Author
    sickn33
    Source
    github.com/sickn33/agentic-awesome-skills/tree/e9809578fd426a284af017c5db99f8eb6628e6ca/skills/ai-agent-security
    Licence
    MIT

    Notice

    « ai-agent-security » (sickn33, 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.