> This page is for version v0.24.0.
> For other versions, use one of these documentation indexes:
> - Latest (default): https://docs.nvidia.com/nemo/guardrails/latest/llms.txt
> - v0.24.1: https://docs.nvidia.com/nemo/guardrails/v0.24.1/llms.txt
> - v0.24.0: https://docs.nvidia.com/nemo/guardrails/v0.24.0/llms.txt
> - v0.23.0: https://docs.nvidia.com/nemo/guardrails/v0.23.0/llms.txt
> - v0.22.0: https://docs.nvidia.com/nemo/guardrails/v0.22.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# nemoguardrails.library.sensitive_data_detection.actions

## Module Contents

### Functions

| Name                                                                                                                              | Description                                                   |
| --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------- |
| [`_get_ad_hoc_recognizers`](#nemoguardrails-library-sensitive_data_detection-actions-_get_ad_hoc_recognizers)                     | Helper to compute the ad hoc recognizers for a config.        |
| [`_get_analyzer`](#nemoguardrails-library-sensitive_data_detection-actions-_get_analyzer)                                         | -                                                             |
| [`_mask_sensitive_data_outcome`](#nemoguardrails-library-sensitive_data_detection-actions-_mask_sensitive_data_outcome)           | -                                                             |
| [`_sensitive_data_detection_outcome`](#nemoguardrails-library-sensitive_data_detection-actions-_sensitive_data_detection_outcome) | -                                                             |
| [`detect_sensitive_data`](#nemoguardrails-library-sensitive_data_detection-actions-detect_sensitive_data)                         | Checks whether the provided text contains any sensitive data. |
| [`mask_sensitive_data`](#nemoguardrails-library-sensitive_data_detection-actions-mask_sensitive_data)                             | Checks whether the provided text contains any sensitive data. |

### Data

[`log`](#nemoguardrails-library-sensitive_data_detection-actions-log)

### API

```python
nemoguardrails.library.sensitive_data_detection.actions._get_ad_hoc_recognizers(
    sdd_config: nemoguardrails.rails.llm.config.SensitiveDataDetection
)
```

Helper to compute the ad hoc recognizers for a config.

```python
nemoguardrails.library.sensitive_data_detection.actions._get_analyzer(
    score_threshold: float = 0.4
)
```

```python
nemoguardrails.library.sensitive_data_detection.actions._mask_sensitive_data_outcome(
    source: str,
    original_text: str,
    masked_text: str
) -> nemoguardrails.actions.rail_outcome.RailOutcome
```

```python
nemoguardrails.library.sensitive_data_detection.actions._sensitive_data_detection_outcome(
    has_sensitive_data: bool
) -> nemoguardrails.actions.rail_outcome.RailOutcome
```

```python
nemoguardrails.library.sensitive_data_detection.actions.detect_sensitive_data(
    source: str,
    text: str,
    config: nemoguardrails.RailsConfig,
    kwargs = {}
) -> nemoguardrails.actions.rail_outcome.RailOutcome
```

async

Checks whether the provided text contains any sensitive data.

Args
source: The source for the text, i.e. "input", "output", "retrieval".
text: The text to check.
config: The rails configuration object.

Returns
RailOutcome.block() if sensitive data has been detected, RailOutcome.allow() otherwise.

```python
nemoguardrails.library.sensitive_data_detection.actions.mask_sensitive_data(
    source: str,
    text: str,
    config: nemoguardrails.RailsConfig
) -> nemoguardrails.actions.rail_outcome.RailOutcome
```

async

Checks whether the provided text contains any sensitive data.

Args
source: The source for the text, i.e. "input", "output", "retrieval".
text: The text to check.
config: The rails configuration object.

Returns
RailOutcome.transform() with the altered text if it changed, RailOutcome.allow() otherwise.

```python
nemoguardrails.library.sensitive_data_detection.actions.log = logging.getLogger(__name__)
```