Browser Extension
Protect ChatGPT, Claude, Gemini, Copilot, Perplexity, and DeepSeek prompts in the browser with FireGuard input guardrails.
Use the Fireraven browser extension when you want FireGuard to check prompts on consumer AI chat sites before they reach the model. The extension runs input guardrails only.
Supported Sites
Supported Browsers
Chrome
Edge
Firefox
Brave
Safari (planned)
Store listings roll out over time. When a listing is published, the activation email includes a download button for that browser. Until then, follow your administrator’s install instructions.
Get an Activation Code
Platform users
- Open the Fireraven app.
- Go to Connectors → Browser extension.
- Click Generate new activation code and enter the email that should receive the code.
End users
Organization owners invite end users from Settings → Organization → End Users. Invitees receive the same activation email (one-time code; no platform login required).
Install and Activate
- Install the Fireraven browser extension for your browser (use the link in the activation email when available, or your admin’s package).
- Open the extension → Set up credentials → Activate with code.
- Enter the email and one-time activation code from the email. Codes expire (default 7 days) and work once.
- Credentials are stored in the browser. FireGuard shows as connected.
Paste Credentials
If you already have platform access, you can skip the activation code:
- Open the extension → Set up credentials → Paste credentials.
- Enter your FireGuard API key and project ID (optional organization ID).
See FireGuard API keys and Project configuration.
What It Does
On Send / Enter, the extension pauses the outbound chat request, calls FireGuard input_guardrails, then:
| Result | Behavior |
|---|---|
| Unsafe | Block the send |
| Safe | Allow the original prompt |
| Out of credits | Allow and show a warning toast |
| Not connected, timeout, or API/bridge error | Allow and show a toast (connect or contact support) |
Output guardrails are not applied by the extension today.
Notes
- Input guardrails only — model output is not checked by the extension.
- Fail-open on infrastructure or credential problems; only policy/security unsafe results block.
- Users can disable or remove the extension in the browser.
- If a site changes its request format and the prompt cannot be extracted, the send may proceed without a FireGuard check.