Skip to content
Sonomos Docs

Send Guard

Send Guard is Sonomos’s safety net for websites that don’t have dedicated Cloak support. It warns you — or blocks submission entirely — when PII is detected in text you’re about to send.

How it works

When you’re on a site that Cloak doesn’t natively cover, Send Guard monitors form fields and text inputs. If Dagger detects PII in content you’re about to submit:

A non-blocking warning banner appears at the top of the input area, listing the detected PII categories. You can dismiss the banner and proceed, or edit your text to remove sensitive data.

Blocking modal

For high-severity detections (SSNs, credit card numbers, medical records), a modal overlay prevents submission. You must explicitly acknowledge the risk or remove the PII before the form will submit. Each detected item can be individually reviewed and toggled.

When Send Guard activates

Send Guard runs on every site that isn’t covered by Cloak’s automatic masking. Currently, Cloak supports Claude.ai, Gemini, and Grok. All other websites get Send Guard automatically.

Configuration

Send Guard is enabled by default. You can adjust its behavior in the Sonomos popup:

  • Banner + Modal (default) — banner for medium, modal for high severity
  • Banner only — warnings only, no blocking
  • Off — disable Send Guard entirely (not recommended)