redact-pii-for-tracing

Official

Secure LLM Observability by Redacting PII

AuthorContextJet-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the challenge of handling sensitive data in LLM observability, ensuring that personally identifiable information (PII) is not inadvertently shared with third-party tracing backends.

Core Features & Use Cases

  • PII Redaction: Safely trace LLM applications without exposing sensitive data.
  • Self-hosting Options: Recommendations for self-hosting solutions to maintain data privacy.
  • SaaS Backend Redaction: Instructions for redacting PII before exporting data to SaaS backends.
  • Metadata-only Capture: Guidance on capturing metadata instead of content for enhanced observability.
  • Use Case: Ideal for financial or healthcare applications where compliance with GDPR/HIPAA/SOC2 is critical.

Quick Start

Run the 'redact-pii-for-tracing' skill to automatically redact PII from LLM traces before exporting them to a third-party tracing backend.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: redact-pii-for-tracing
Download link: https://github.com/ContextJet-ai/awesome-llm-observability/archive/main.zip#redact-pii-for-tracing

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.