> ## Documentation Index
> Fetch the complete documentation index at: https://platform.atlan.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the atlanai CLI; `atlanai --map json` prints its command map. Run a read-only identity check before any write.
> The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects.
> SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript.

# Security

> Understand the planned skill security review.

# Skill security

The **Security** tab describes the security review planned for skills. It does
not run a scan, report findings, or block a release yet. Treat this page as a
product preview, not as evidence that a skill is safe.

<Warning>
  The planned scores, findings, trend, and release gate are illustrative. They
  are not the result of a live scan.
</Warning>

## What the preview covers

* **Security posture:** A risk score and a recommendation such as Safe, Caution,
  or Do not install.
* **Scan coverage:** The patterns, categories, and analyzers included in the
  scan.
* **Findings:** Severity, file location, confidence, and suggested remediation.
* **Risk trend:** How the score changed across versions or scans.
* **Release gate:** Whether a finding would be advisory or block promotion.

## What to do today

Review the package in **Source** before you use or publish it. Check every
supporting file, especially scripts and templates, and use the selected
version's source rather than a name alone. Follow your organization's review
process until the Security tab can provide verified scan results.