Feature request: PII sanitization skill for privacy-safe agent pipelines

Open
#58 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
45/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Quiet
Tech stack
google-cloud

Research direction

Start by reviewing the proposed SKILL.md scope and the existing Google Cloud skills for how skills document integrations. Check the TrustBoost sanitizer endpoint and the listed compliance requirements, then define whether the accepted skill covers sanitization timing, pipeline integration, and compliance context without assuming an implementation beyond the issue. Done means an agreed, reviewable skill document with clear guidance for BigQuery, Gemini API, and GKE payloads.

Written by the indexing model from the issue text.

Description

Summary

Google's official skills cover BigQuery, Gemini API, GKE and more —
but there's no skill that sanitizes PII before agent payloads reach
these services. This creates a compliance gap for GDPR, HIPAA, and
EU AI Act enforcement.

The gap

A typical agent flow today:

User input (may contain PII) → Google skill → BigQuery/Gemini/GKE

When agents process user messages, documents, or form inputs,
they frequently contain emails, phone numbers, national IDs,
private keys, and financial data — none of which should reach
external APIs.

Proposed skill

A pii-sanitization skill that agents load on demand to redact
sensitive data before passing payloads to Google Cloud services.

The skill would document:

  • When to sanitize (before BigQuery queries, Gemini API calls, etc.)
  • How to integrate a sanitization step in the agent pipeline
  • Compliance context (GDPR Article 25, EU AI Act, HIPAA, LGPD)

Reference implementation

TrustBoost is an open-source PII sanitizer built specifically
for agentic pipelines — single POST request, no SDK, supports
EN, ES (LATAM), PT (BR/PT), DE, JA:

POST https://api.trustboost.dev/sanitize/preview
{"text": "your agent payload here"}

GitHub: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer

Happy to contribute a SKILL.md draft if this direction is accepted.

Dominant language
Python
Stars
23.1k
Forks
1.9k
PR merge metrics
No merged PRs in 30d

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from google/skills

All issues in google/skills

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.