PII Guard for Claude Code: Open-source plugin redacts sensitive data before LLM processing
By
Antonio Maiolo
Hard crust, hollow middle. Skim only.
Summary
An open-source plugin called "PII guard for Claude Code" that redacts personally identifiable information (PII) such as names, emails, and IBANs before sending data to Claude Code. The tool replaces sensitive data with placeholders that Claude sees, while the originals remain local and can be revealed by the user. The same engine is also available as a CLI tool for any LLM and as a hosted proxy for OpenAI, Anthropic, and Azure services.
Key quotes
· 3 pulledOpen-source plugin that redacts PII before Claude Code reads it.
Names, emails, and IBANs become placeholders Claude sees; you reveal originals locally.
Same engine ships as a CLI for any LLM and a hosted proxy for OpenAI/Anthropic/Azure.
You might also wanna read
Anthropic releases open-source legal workflow plugins for Claude AI
Anthropic has released an open-source suite of plugins called "Claude for Legal" designed for legal workflows. The repository provides refer
github.com·17d ago
PII-Shield: Kubernetes Sidecar for Automated Log Sanitization and PII Redaction
PII-Shield is a zero-code Kubernetes sidecar solution for log sanitization that automatically detects and redacts Personally Identifiable In
github.com·26d ago
Anthropic Releases Claude Code Security AI Tool to Help Defenders Detect Vulnerabilities
Anthropic is releasing Claude Code Security, an AI-powered cybersecurity tool designed to help defenders detect novel, high-severity vulnera
anthropic.com·3mo ago
Local-First Reversible PII Scrubber for AI Workflows Using ONNX and Regex
The article discusses a technical solution to the privacy-translation paradox in AI workflows, where teams need to translate user content us
medium.com·5mo ago
Claw-Coder: A locally-run AI coding agent with RAG and knowledge graph for privacy-focused development
Claw-Coder is a locally-run AI agent designed to address privacy and security concerns associated with cloud-based coding agents like Claude
news.ycombinator.com·8d ago
Pipelock: Open-Source Firewall for AI Agent Security with DLP Scanning and SSRF Protection
Pipelock is an open-source firewall for AI agents that provides security at the boundary between AI systems and external networks. It offers
github.com·3mo ago