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

# FTLSecretDetection

> Evaluator to detect credentials, API keys, and tokens in text using Fiddler Centor Models.

Evaluator to detect secrets and credentials in text using Fiddler Centor Models.

The FTLSecretDetection evaluator scans text for API keys, tokens, and credentials, covering
\~42 known credential formats plus detection of unknown secrets. It is deterministic and
low-latency.

Key Features:

* **Known-format detection**: \~42 known credential formats across LLM providers, cloud platforms, source control, messaging, and developer tools
* **Unknown secret detection**: Catches unknown or custom secrets that don't match a known format (labeled `Possible Secret`)
* **Fast**: Sub-millisecond latency — no inference overhead

Use Cases:

* **Secret leakage detection**: Identify credentials in LLM prompts or responses
* **Compliance auditing**: Scan text datasets for inadvertently captured credentials
* **Data sanitization**: Locate and redact secrets in datasets before training or fine-tuning

Scoring Logic:

Unlike probability-based evaluators, FTLSecretDetection returns one `Score` per detected secret:

* **No secrets detected**: Returns an empty list
* **Secrets detected**: Returns one `Score` per detection, with `name` set to the secret type label and `value` set to `1.0`

To retrieve character-level positions for redaction, use the REST API directly — see [Secret Detection tutorial](https://docs.fiddler.ai/developers/tutorials/guardrails/guardrails-secrets.md).

## Parameters

* **text** (*str*) – The text to scan for secrets and credentials.
* **score\_name\_prefix** (*str* *|* *None*)
* **score\_fn\_kwargs\_mapping** (*ScoreFnKwargsMappingType* *|* *None*)

## Returns

A list of Score objects, one per detected secret:

* name: The secret type label (e.g., `"Anthropic API Key"`, `"AWS Access Key ID"`)
* evaluator\_name: `"FTLSecretDetection"`
* value: `1.0` for each detection (binary — present or absent)

## Raises

**ValueError** – If the text is empty or None.

## Example

```python theme={null}
from fiddler_evals.evaluators import FTLSecretDetection

evaluator = FTLSecretDetection()
```

```python theme={null}
# Clean text — no secrets
scores = evaluator.score("What is the weather like today?")
print(f"Secrets found: {len(scores)}")
# Secrets found: 0

# Text containing an API key
scores = evaluator.score(
    "My Anthropic key is sk-ant-api03-abcdefghijklmnopqrstu"
)
for score in scores:
    print(f"Detected: {score.name} (value={score.value})")
# Detected: Anthropic API Key (value=1.0)

# Check whether any secrets were found
has_secrets = len(scores) > 0
secret_types = [score.name for score in scores]
print(f"Secret types found: {secret_types}")
# Secret types found: ['Anthropic API Key']
```

> [!NOTE]
>
> FTLSecretDetection uses a lightweight, deterministic detection engine rather than an ML
> model. Known credential formats are detected reliably, though random-looking non-secret
> strings may occasionally be flagged as `Possible Secret`.

## name

**Value:** `'ftl_secret_detection'`

## score()

Scan a text string for secrets and credentials.

### Parameters

**text** `str` *required*

The text to scan for secrets and credentials.

### Returns

A list of Score objects, one per detected secret. Empty list if no secrets found.
