API keys
AWS keys, OpenAI tokens, GitHub PATs, Stripe live keys: all routinely pasted into ChatGPT for debugging help. Every paste is a one-way leak.
$ grep -r 'sk-' ~/chats/*
→ 47 matches in 12 files
system · operational
build / 5.1.7scope / 19 hostsegress / 0 callsblocked today / 0
[ 0xVB·CRT ]Open source · 100% local · no account
Stop pasting
API keys into
ChatGPT.
VaultBix catches API keys, customer data, and proprietary code before they leave your browser. 100% local. No account.
Open source · No tracking · Works on ChatGPT, Claude, Cursor, Copilot, Gemini, Perplexity + more
For teams: audit logs · SSO · custom rules · coming soon
chatgpt.com / promptvaultbix · live
1 Live capture from a real prompt. Replay every 6s.
★ 5.0 chrome web store100% localzero data collectionopen source
Engineers leak
secrets into AI
tools every day.
Most teams have no defense. "Don't paste sensitive stuff" is not a security strategy. It's a hope.
Customer data
PII, customer records, internal IDs, pasted into prompts without thinking about where it ends up.
Proprietary code
Internal architectures, business logic, security implementations: all shipped to AI providers' training pipelines.
74%
devs use AI daily
38%
admit pasting secrets
0
rotation after leak
How VaultBix protects you.
01/install
Install in 30 seconds
Free Chrome extension. No account. No setup required.
~ chrome web store › add to chrome
02/scan
We scan, locally
Detects 45+ types of secrets (API keys, JWTs, SSNs, credit cards, private keys) using regex + entropy analysis. 100% local. Nothing sent to any server.
~ regex + shannon entropy · runtime ≈ 1ms
03/protect
Block, redact, or warn
Choose your sensitivity. Strict mode blocks the request. Balanced warns on critical leaks. You stay in control.
~ policy: strict | balanced | passive
45 detection
patterns and counting.
Each pattern is regex-anchored and entropy-checked. Every false-positive we hear about gets a unit test the same week.
~/vaultbix/detect/patterns.ts15 active
API Keys07 patterns
AKIA…AWS Access Keyssk-… sk-proj-OpenAI Keyssk-ant-…Anthropic Keysghp_…GitHub PATssk_live_…Stripe Live Keysglpat-…GitLab Tokensxoxb-…Slack Tokens- + 10 more patterns →
Credentials04 patterns
eyJ…JWT Tokenspostgres://…DB Connection Strings-----BEGIN…Private Keys (SSH/RSA/PGP)Bearer …Auth Tokens
Personal Data04 patterns
###-##-####Social Security Numbers4… 5… 3…Credit Cards (Luhn-validated)user@…Email Addresses+1 (###)…Phone Numbers
Works where
you work.
Adding more sites monthly. Request one in our GitHub issues and we'll wire it up.
ChatGPTClaudeGeminiMicrosoft CopilotGitHub CopilotCursorPerplexityGrokDeepSeekMistralHuggingFacePoeYou.comChatGPTClaudeGeminiMicrosoft CopilotGitHub CopilotCursorPerplexityGrokDeepSeekMistralHuggingFacePoeYou.com
host_permissions: 19 explicit hosts · no all_urls.
Your secrets
never leave
your browser.
Three claims you can verify yourself. Click through to the file in the repo if you want the receipts.
View source on github100% local detection
All scanning happens in your browser using regex + entropy analysis. We don't send your prompts anywhere. Period.
$ grep -rn 'fetch\|XMLHttpRequest' src/detect/
→ 0 results · zero egress in detection path
Hashed storage
Even your local incident log uses SHA-256 hashes, never the raw secret values. PII gets zero prefix exposure.
Open source
Read the code yourself. Audit our network calls (there are zero for free users). Verify our claims are real.
§07 / Org tier · in designBuilding a team plan
Building a team plan
for engineering orgs.
Centralized policy controls, an org-wide incident dashboard, SSO, audit logs, custom detection rules, and SIEM integration. Coming soon for engineering teams.
Email founders@vaultbix.com⌁ design partners get free seats for life
- 01Centralized policy controlsplanned
- 02Org-wide incident dashboardplanned
- 03SSO (Okta, Google, Entra)planned
- 04Audit logs with hash-only eventsplanned
- 05Custom detection rulesplanned
- 06SIEM integration (Splunk / Datadog)planned
§08 / MaintainersBuilt by two
Built by two
high school
seniors.
We're Carl Gao and Max Alexandre. We built VaultBix after watching engineers (including ourselves) paste real production secrets into ChatGPT while debugging.
Five months and 45 detection patterns later, here we are. The product is open source because trust matters more than secrecy when you're in the business of handling secrets.
Questions,
answered.
If something isn't covered here, ask in our GitHub issues or email founders@vaultbix.com. We answer fast.
q.01Is this really 100% local?
Yes. Open the GitHub repo and search for "fetch" or "XHR" calls. The free version makes zero network requests for detection. Only the optional team tier syncs incident metadata (hashes only, never raw values) to a backend.
q.02Why should I trust a Chrome extension?
We use 19 specific host_permissions (chatgpt.com, claude.ai, etc.), not broad "all_urls". Only "storage" and "tabs" permissions. Open source so you can verify yourself.
q.03Does this slow down my browser?
No measurable impact. Detection runs in ~1ms per request on the page-world script.
q.04What about Firefox?
On the roadmap. Chrome first because that’s where adoption is.
q.05How does this work with Cursor / Claude Code / Windsurf?
Browser-based tools (chatgpt.com, claude.ai, gemini.com) are protected today. IDE-based agents are on the v5.2 roadmap.
q.06Is the team plan available now?
Coming soon. Email founders@vaultbix.com to be a design partner.
§10 / install