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

# Security

> Security best practices for agents

Security features protect your agents and data.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Security Layers"
        A[🤖 Agent] --> G[🛡️ Guardrails]
        G --> P[📜 Policies]
        P --> S[🔒 Sandbox]
    end
    
    classDef agent fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef security fill:#10B981,stroke:#7C90A0,color:#fff
    
    class A agent
    class G,P,S security
```

## Quick Start

<Steps>
  <Step title="Apply Security">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{Agent, SecurityConfig};

    let config = SecurityConfig::new()
        .allow_network(false)
        .allow_fs(false)
        .data_encryption(true);

    let agent = Agent::new()
        .name("Secure Bot")
        .security(config)
        .build()?;
    ```
  </Step>
</Steps>

***

## Security Features

| Feature    | Description        |
| ---------- | ------------------ |
| Guardrails | Content validation |
| Policies   | Behavior rules     |
| Sandbox    | Isolated execution |
| Encryption | Data protection    |

***

## Best Practices

> \[!CAUTION]
> Always validate user input and restrict agent permissions in production.

***

## Related

<CardGroup cols={2}>
  <Card title="Guardrails" icon="shield" href="/docs/rust/guardrails">
    Content validation
  </Card>

  <Card title="Sandbox" icon="box" href="/docs/rust/sandbox">
    Isolated execution
  </Card>
</CardGroup>