◉ClassyGitShadowzzh

sensitive-data.mdx

sensitive-data.mdx
---
title: "Sensitive Data"
description: "Handle secret information securely and avoid sending PII & passwords to the LLM."
icon: "shield"
mode: "wide"
---


```python
import os
from browser_use import Agent, Browser, ChatOpenAI
os.environ['ANONYMIZED_TELEMETRY'] = "false"


company_credentials = {'x_user': 'your-real-username@email.com', 'x_pass': 'your-real-password123'}

# Option 1: Secrets available for all websites
sensitive_data = company_credentials

# Option 2: Secrets per domain with regex
# sensitive_data = {
#     'https://*.example-staging.com': company_credentials,
#     'http*://test.example.com': company_credentials,
#     'https://example.com': company_credentials,
#     'https://google.com': {'g_email': 'user@gmail.com', 'g_pass': 'google_password'},
# }


agent = Agent(
    task='Log into example.com with username x_user and password x_pass',
    sensitive_data=sensitive_data,
    use_vision=False,  #  Disable vision to prevent LLM seeing sensitive data in screenshots
    llm=ChatOpenAI(model='gpt-4.1-mini'),
)
async def main():
await agent.run()
```

## How it Works
1. **Text Filtering**: The LLM only sees placeholders (`x_user`, `x_pass`), we filter your sensitive data from the input text.
2. **DOM Actions**: Real values are injected directly into form fields after the LLM call

## Best Practices
- Use `Browser(allowed_domains=[...])` to restrict navigation
- Set `use_vision=False` to prevent screenshot leaks  
- Use `storage_state='./auth.json'` for login cookies instead of passwords when possible