Flags names, numbers and other personal data in the Claude and AlmmaGPT message box before sending. Runs only on your computer.
Users
1
store count
Rating
0.0 / 5
unchanged in 30 days
Ratings
0
total ratings
Store rank
#364K
#299K among extensions
Version
0.3.2
updated 18 Nov 2026
Publisher and listing changes
From our daily record of this listing since 18 Nov 2026
No change of publisher name, contact email, website, privacy policy or listing name since 18 Nov 2026.
About Almma’s PII Guard
PII Guard checks what you paste or type into the message box on claude.ai and chat.almma.ai, and catches personal data before it leaves your computer.
• Paste: the text is held back first. A review panel shows every flagged item and the placeholder that will replace it, e.g. John Smith → [NAME_1]. • Typing: flagged text is underlined in red, and sending is paused until you review it. • One key to decide: Enter replaces, Ctrl+Enter keeps the original, Esc cancels. • Reverse it: select the AI's reply, right-click, "show originals" — the real names come back in a private panel, never in the page. • Your rules: switch each rule on or off, add names that must always (or never) be flagged, and add your own patterns.
What it catches: names, e-mail addresses, phone and ID numbers, dates, street addresses, web and IP addresses, ages over 89, medical record, policy and account numbers, vehicle numbers — the text-based identifiers in the HIPAA Safe Harbor list, plus student names and IDs relevant to FERPA.
Private by design: PII Guard contains no network code. No servers, no analytics, no account. The placeholder key lives in memory and is erased when the browser closes.
PII Guard lowers the risk of sharing personal data; it does not by itself make your use of an AI service compliant with FERPA, HIPAA or any other law. It does not inspect attached files or images.
Version history
1 versions recorded
No update since 18 Nov 2026 changed the permissions or site access.