Veil a Drop-in PII redaction proxy for any LLM API

Name: Veil a Drop-in PII redaction proxy for any LLM API
Availability: InStock
Author: A5omic

by A5omic·Apr 7, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerWizardrySolve My Problem

Stops zero-width Unicode bypasses that break standard PII filters before LLM calls.

Strengths

•Normalizes Unicode to prevent zero-width character bypass attacks on PII detection.
•Streaming support with only 23ms overhead is impressive for a security proxy.
•Supports 41 LLM providers with a single API key swap and no SDK changes.

Weaknesses

•Adds a third-party dependency to the LLM request path which could be a risk.
•Free tier limited to 100 requests/month might hinder thorough testing for teams.

Post Description

I was building a proxy to strip PII from LLM API calls and realized that zero-width Unicode characters break basically every PII filter out there. If you stick a zero-width space inside a name like T om, Presidio's NER model doesn't see it as a name anymore. Same thing with SSNs and phone numbers against regex. So I built a normalization layer that strips all that stuff before running detection.

The proxy itself is pretty simple. You swap your OpenAI base URL to point at Veil and it redacts PII before the request leaves, then puts the real values back in the response. Works with streaming too which was the hard part honestly.

https://veil-api.com, free tier is 100 requests/month.