> For the complete documentation index, see [llms.txt](https://ai-security-docs.akto.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-security-docs.akto.io/agentic-guardrails/how-to/create-guardrail-policies/access-restrictions-and-exceptions.md).

# Access Restrictions and Exceptions

Restrict which hosts, paths, and accounts can interact with your agents, and define phrases a policy should treat as safe.

This page covers part of the [Create Guardrail Policies](https://ai-security-docs.akto.io/agentic-guardrails/how-to/create-guardrail-policies.md) form.

## Access Restrictions

Configure controls to restrict which hosts, paths, and account types can interact with your agents.

**Block host / path**

Block outbound traffic by host or path pattern to prevent agents from reaching unauthorised external services or endpoints.

{% stepper %}
{% step %}
**Enter a pattern**

Enter a host or path pattern in the **Host or path pattern** field.
{% endstep %}

{% step %}
**Add it to the list**

Select **Add** to include the pattern in the blocked list.
{% endstep %}
{% endstepper %}

The **Blocked patterns** list displays all configured entries. You can review and remove patterns from this list at any time.

{% hint style="info" %}
Akto sits between your agents and their outbound traffic. When a request is made, Akto checks the destination host or path against the blocked patterns and denies any match before it reaches the target.
{% endhint %}

**Block personal accounts**

Prevent users with personal or consumer email accounts from accessing the AI agent. Enterprise accounts using company email domains are allowed through.

* Enable **personal account blocking** to restrict access to organisation-managed accounts only.

**Block public sharing**

Block chats and artifacts from being shared through public links, so conversations and generated content stay inside your organisation.

* Enable **public sharing blocking** to stop users from creating public links to chats and artifacts in supported AI tools.

{% hint style="info" %}
Personal account blocking is enforced through the [browser extension](https://ai-security-docs.akto.io/akto-atlas-agentic-ai-security-for-employee-endpoints/endpoints-discovery-agents/browser-extensions/chrome/extension-usage-behaviour.md), and currently supports the following browser LLMs: **chatgpt.com**, **gemini.google.com**, **claude.ai**, **copilot.microsoft.com**, and **grok.com**. Requires Akto browser extension v1.0.69 or later; it is currently supported only through the browser extension, with AI Endpoint Shield Agent support coming soon.
{% endhint %}

<div data-with-frame="true"><figure><img src="https://1895868029-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkpBG2Nfd5ZbNmahr8W6H%2Fuploads%2Fgit-blob-d4edf4cdd69cdc3b3e2a3d81d6a72920d98961ab%2Fimage%20(177).png?alt=media" alt="" width="563"><figcaption></figcaption></figure></div>

## Exceptions

Configure phrases that this policy's own detectors should treat as safe and skip, without affecting how other guardrail policies evaluate the same traffic.

**Ignore Phrases**

{% stepper %}
{% step %}
**Enter a phrase**

Enter a phrase in the **Ignore phrases** field (e.g. your product name or sample test data). Phrases are matched as a whole word by default.
{% endstep %}

{% step %}
**Set matching options (optional)**

Enable **Regex** to match the entry as a regular expression instead of literal text. Enable **Case sensitive** to match the phrase's casing exactly.
{% endstep %}

{% step %}
**Add the phrase**

Select **Add phrase** to include it in the ignored list.
{% endstep %}
{% endstepper %}

<div data-with-frame="true"><figure><img src="https://1895868029-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkpBG2Nfd5ZbNmahr8W6H%2Fuploads%2Fgit-blob-3d7c098a500989c41fca831195a8a554ed3ed969%2Fimage%20(220).png?alt=media" alt="" width="563"><figcaption></figcaption></figure></div>

The **Ignored phrases** list displays a count of configured entries and lets you remove any phrase at any time.

{% hint style="info" %}
Ignore phrases only affect this policy's own detectors, so other guardrail policies evaluated on the same traffic still see the real text.
{% endhint %}
