autoresearch-privacy-guard

Scan Dart and Python code to redact PII patterns with grep verification.

Updated Jan 25, 2026
One-click install
npx skills add https://github.com/MINT-IA/MINT --skill autoresearch-privacy-guard
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoresearch-privacy-guard
Source: https://github.com/MINT-IA/MINT/tree/main/.claude/skills/autoresearch-privacy-guard
Command: npx skills add https://github.com/MINT-IA/MINT --skill autoresearch-privacy-guard

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents accidental leakage of personally identifiable information (PII) into logs, analytics, and LLM context by scanning source code and autonomously redacting sensitive values before they can be recorded or transmitted.

Core Features & Use Cases

  • Automated PII scanning: Runs targeted grep-style phases over Dart and Python code to find prints, analytics, CoachContext construction, LLM prompts, and SharedPreferences usage.
  • Pattern-based anonymization: Replaces detected IBANs, AVS/AHV numbers, emails, phones, NPAs, salaries, and employer names with standardized redacted tokens or ranges.
  • Verification-first workflow: Requires fresh grep verification and flutter test results before committing fixes, with strict time and single-file iteration constraints.
  • Use Case: Run a full repository scan to locate CRITICAL PII leaks in mobile app CoachContext and analytics calls, automatically redact one file at a time, verify the fix, and commit the change.

Quick Start

Run /autoresearch-privacy-guard to scan the repository, redact identified PII in one file at a time, verify with grep and flutter test, and commit verified fixes.

Frequently Asked Questions about autoresearch-privacy-guard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically redact PII in Flutter source code and logs?

To redact PII in Flutter source code and logs, run an automated grep-style scan over Dart files to detect prints, analytics calls, and SharedPreferences usage. It replaces sensitive values like emails and AVS numbers with standardized redacted tokens before committing.

What is the best way to prevent sensitive data leakage in Python backend analytics?

Preventing sensitive data leakage in Python backend analytics involves scanning source code to identify exposed IBANs, salaries, and employer identifiers. Pattern-based anonymization rules automatically replace these values with standardized ranges or tokens to ensure compliance.

Can I use grep to find and anonymize emails and phone numbers in LLM prompts?

Yes, you can use grep-style detection to find and anonymize emails and phone numbers in LLM prompts. The tool scans CoachContext constructions and applies pattern-based anonymization rules to replace detected sensitive values with safe tokens.

Does the PII redaction workflow support flutter test verification?

Yes, the PII redaction workflow supports flutter test verification. It enforces a verification-first approach that requires fresh grep results and passing flutter test outputs before autonomously committing any single-file redaction fixes.

How do I scan source code for Swiss AVS numbers and IBANs to ensure compliance?

Scanning source code for Swiss AVS numbers and IBANs involves running targeted grep-style detection phases across Dart and Python environments. It identifies these specific patterns in logs and analytics, applying standardized redacted tokens to maintain compliance.