Security●●●Banger
Secret Sanitizer – auto-masks secrets when you paste into AI chats
Intercepts pastes, masks 30+ secret types locally—zero network requests or tracking.
Solve My ProblemSlick
souvikghosh957
103mo ago
Back to browse
GitHub Repository
A blazingly fast PII masker that swaps real secrets for realistic fakes.
1 starsRust
Created a tool that prevents accidental pasting of PII in AI prompts
by thomscoder·Mar 16, 2026·1 point·0 comments
AI Analysis
●●SolidSolve My ProblemShip It
Four-pass detection with deterministic fakes beats simple regex redaction tools.
Strengths
- •Four-pass detection in single linear scan — structural, contextual, and entropy-based
- •Deterministic fakes preserve data structure so AI can still reason on masked input
- •Works as PTY proxy wrapping any AI tool — Claude, Cursor, or custom commands
Weaknesses
- •Early stage with 8 commits — author admits it still slips data or returns false positives
- •Secret scanning already exists in pre-commit hooks and IDE extensions like GitGuardian
Category
Target Audience
Developers using AI coding assistants
Similar To
GitGuardian · Presidio · Microsoft Presidio
Post Description
Shhh (i didn't have any idea for the name) is really fast PII masker that swaps real secrets for realistic fakes, preserving the data’s structure so your AI tools can reason on it without ever seeing the originals. It can wrap your AI tool to prevent accidental direct pasting of PII and secrets. Play with the playground https://shhh-7c4.pages.dev/
It is still being improved (any contribution are welcomed) so it still slips things or may return false positives.
Hope you guys will like it!
Similar Projects
Security●●Solid
ChatGPT gets your prompt before you hit send
Isolated browser extension overlay intercepts keystrokes ChatGPT can't read—but users still trust OpenAI with unmasked context.
Solve My ProblemDark HorseShip It
phico
373mo ago
Security●●●Banger
Passwd.page – give agents secrets without pasting them into prompts
Typed secret schemas for agents beat pasting API keys into LLM prompts.
Solve My ProblemBig Brain
davidfeldi
101d ago
Productivity●Mid
Chatbot to reuse AI prompts instead of copy-pasting
Prompt template reuse is useful, but ChatGPT, Notion, and Raycast already do this.
Ship It
owenthecoder13
103mo ago
Security●●Solid
PrivacyShield – Mask your PII before it reaches ChatGPT/Claude
Local PII masking for ChatGPT—free and zero-server, but detection accuracy unverified.
Solve My ProblemDark HorseSlick
BuddhikaR
113mo ago
Security●●Solid
FunWithText – Free browser PII sanitizer and prompt injection scanner
Runs fully in the browser for regex-based redaction of structured PII (emails, cards, phones, API keys, IPs, SSNs) and offers an optional Claude step to catch names/addresses patterns miss. Clear placeholders like [NAME] and a privacy toggle make it practical for quick, manual workflows, and I like the Norwegian NIN/phone support. It's useful and thoughtfully privacy-first but not novel — the real win would be integrations (batch processing, editor/extension) or independent accuracy metrics for the AI step.
Solve My ProblemSlickNiche Gem
atbj
203mo ago