> ## 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 • AI Agents Framework

> praisonai.security — Agent security utilities for PraisonAI.

# security

AI Agents Framework

praisonai.security — Agent security utilities for PraisonAI.

Provides:

* Prompt injection defense (6-check pipeline)
* Append-only audit log for tool calls
* Protected paths guard for code tools

All features are opt-in with zero overhead when not enabled.

Usage (simplest):
from praisonai.security import enable\_security
enable\_security()

from praisonaiagents import Agent
agent = Agent(instructions="You are a researcher")
agent.start("Research the latest AI news")

Usage (selective):
from praisonai.security import enable\_injection\_defense, enable\_audit\_log
enable\_injection\_defense()
enable\_audit\_log()

## Import

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai import security
```

## Functions

> [card] [enable\_injection\_defense()](https://praison.ai/docs/sdk/reference/praisonai/functions/enable_injection_defense.md)
>
> Enable prompt injection defense globally for all agents.

> [card] [enable\_audit\_log()](https://praison.ai/docs/sdk/reference/praisonai/functions/enable_audit_log.md)
>
> Enable an append-only JSONL audit log for all agent tool calls.

> [card] [enable\_security()](https://praison.ai/docs/sdk/reference/praisonai/functions/enable_security.md)
>
> Enable all security features in one call.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.