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

# Sensitive Data

> Detect, audit, and optionally redact secrets, PII, sensitive data access, and outbound data flows.

Sensitive-data monitoring helps you understand when agents touch private or risky information. It can flag secrets, personal information, sensitive data columns, credential files, database access, and outbound flows.

Enable it per agent from agent → **Settings** → **General** → **Sensitive data monitoring**.

## Detection modes

| Mode              | What it does                                                                          | Use when                                                       |
| ----------------- | ------------------------------------------------------------------------------------- | -------------------------------------------------------------- |
| **Off**           | No scanning and no overhead                                                           | The agent never handles private data or external sends         |
| **Deterministic** | Fast pattern rules for PII, secrets, credentials, database access, and outbound flows | Default for most agents                                        |
| **Smart**         | Deterministic rules plus a lightweight LLM pass per turn                              | You need to catch obfuscated or domain-specific sensitive data |

Smart mode can reduce false positives and catch values the rules miss, such as a phone number written in words. Smart-only findings are marked **caught by LLM** in traces. They are report-only and add some latency and cost.

## What gets flagged

SlackHive uses broad categories so the audit trail stays readable:

| Category             | Examples                                                                                                                 |
| -------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| **Secret**           | OpenAI keys, Anthropic keys, GitHub tokens, Slack tokens, Stripe keys, JWTs, private keys, connection strings, passwords |
| **Personal info**    | Email addresses, phone numbers, card numbers, SSNs, IBANs                                                                |
| **Sensitive data**   | Data columns or fields such as salary, payment, passport, address, date of birth, bank account, or custom keywords       |
| **Sensitive action** | Database access, credential-file access, or tools that move data out of SlackHive                                        |

Tool input and output are scanned. Agent replies are scanned for values such as PII and secrets.

## Custom guidance

In **Smart** mode, add agent-specific rules under **What's sensitive for this agent**.

Use one rule per line, for example:

```text theme={null}
Internal project codenames: Project Atlas, Bluebird
Unreleased pricing or revenue figures
Patient IDs and support case identifiers
```

This tells the LLM detector what matters for that agent beyond the built-in categories.

## Redaction

Turn on **Redact secrets in replies** when the agent posts into shared channels or reads from sensitive systems. The toggle name is intentionally conservative, but the level you choose controls how much gets masked.

Choose a redaction level:

| Level                  | What gets masked in the outbound reply                                                    |
| ---------------------- | ----------------------------------------------------------------------------------------- |
| **Secrets only**       | API keys, tokens, passwords, private keys, card numbers, SSNs, and other high-risk values |
| **Secrets + PII**      | Secrets plus emails, phone numbers, and other detected personal information               |
| **Everything flagged** | Every detected match, including sensitive data keywords and credential paths              |

Outbound redaction happens before the message reaches Slack. The private trace still records the event for audit, and non-admin viewers see sensitive values masked in trace views.

## Auditing events

Open **Observability → Sensitive** to review flagged sessions.

The Sensitive tab shows:

* Recent sensitive events
* Which agent and session touched the data
* Category and severity
* Whether the event was caught by deterministic rules or Smart mode
* Sensitive data flows, such as data found in an outbound sink

Click an event to open the trace at the exact span. Admins can reveal raw values when needed; other roles see redacted content.

## Operational defaults

Recommended starting point:

| Agent type                         | Detection              | Redaction                                          |
| ---------------------------------- | ---------------------- | -------------------------------------------------- |
| Data analyst, finance, support, HR | Deterministic or Smart | Secrets only, or Secrets + PII for shared channels |
| Engineering/code agents            | Deterministic          | Secrets only                                       |
| Public research or writing agents  | Deterministic          | Off unless they handle user data                   |
| High-risk regulated workflows      | Smart                  | Secrets + PII or Everything flagged                |

## Advanced keyword tuning

Admins can extend deterministic matching from `.env`:

| Variable                  | Purpose                                                               |
| ------------------------- | --------------------------------------------------------------------- |
| `SENSITIVE_DATA_KEYWORDS` | Extra comma-separated data-field keywords to flag in tool arguments   |
| `SENSITIVE_TOOLS`         | Extra comma-separated tool-name fragments to treat as sensitive tools |

Restart SlackHive after changing `.env`.

## Related

<CardGroup cols={2}>
  <Card title="Observability" icon="chart-line" href="/features/observability">
    Review sensitive events, sessions, tools, tokens, and traces.
  </Card>

  <Card title="Agent Evals" icon="shield-check" href="/agents/evals">
    Catch prompt, skill, tool, and behavior regressions before they hit Slack.
  </Card>
</CardGroup>