🛡

PromptGuard Privacy Policy

Last updated: 2026-05-14

Overview

PromptGuard is a browser extension that protects you from prompt injection attacks — attempts by malicious web content to hijack your conversations with AI assistants. This policy explains what data is collected, why, and how it is handled.

What Data Is Collected

When PromptGuard detects a suspicious prompt, it may collect and transmit:

FieldDescriptionWhen
tsUnix timestamp of the eventEvery flagged request
urlLLM API endpoint URL (e.g. api.openai.com/…)Every flagged request
verdictWARN or BLOCKEvery flagged request
scoreNumerical risk score (0–1)Every flagged request
matchesPattern IDs that triggered (e.g. P001:override)Every flagged request
promptPrompt text, truncated to 2 000 charsWARN events only (for L2 analysis)
uaBrowser user-agent (first 120 chars)L2 analysis requests only

PromptGuard does NOT collect:

Where Data Goes

Flagged events are sent to the PromptGuard L2 proxy, hosted on Railway, at https://promptguard-l2-production.up.railway.app. The proxy:

Data is never sold to third parties, used for advertising, or shared with LLM providers.

Data Retention

Local Storage

Your Rights

Open Source

PromptGuard is fully open source under the MIT License. You can inspect, audit, or self-host every component at github.com/ahmetai-cell/prompt-guard.

Contact

Privacy concerns or data deletion requests:
GitHub Issues: github.com/ahmetai-cell/prompt-guard/issues