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.

Harden an agent UI's security v1.0.0

Use this resource to harden the security of an agent-rendered interface

New

  • 564 downloads
  • 217 likes
  • 142 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-ui-security-hardening

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 checks the sandbox model, defines narrow CSP allowlists in _meta.ui.csp and treats all incoming data as untrusted. You get a pre-release checklist and the points to have reviewed.

Mostly picked by

Updated November 2, 2026

Card for the “Harden an agent UI's security” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: sandbox contract and CSP authoring
  • SKILL.md: untrusted structuredContent, prompt injection, secrets and pre-ship checklist

Good fit for

  • Your MCP widget shows data from an external service
  • You must validate an interface before it goes live

Not for

    Tags

    • security
    • csp
    • sandbox
    • prompt injection
    • agent ui

    About

    You say

    “Check the CSP and data handling of my MCP widget before release.”

    Card for the “Harden an agent UI's security” skill

    Skill published by mcp-apps-studio 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 harden the security of an agent-rendered interface
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md7.7 KB

    Origin and licence

    Listed unmodified

    Author
    mcp-apps-studio
    Source
    github.com/thelobbi/claude/tree/f971cbfa27f0d1cd9d885bb9ae0f325dbe90dc27/plugins/mcp-apps-studio/skills/ui-security-sandbox
    Licence
    MIT

    Notice

    « ui-security-sandbox » (mcp-apps-studio, 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.