output-sanitizer

Detect and redact credentials, PII, and internal paths from AI agent output.

70|10|Updated Feb 5, 2026

Search Tags:#security #credentials #data masking #redaction #pii #output sanitization

Ready to run

npx skills add https://github.com/UseAI-pro/openclaw-skills-security --skill output-sanitizer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: output-sanitizer
Source: https://github.com/UseAI-pro/openclaw-skills-security/tree/main/skills/output-sanitizer
Command: npx skills add https://github.com/UseAI-pro/openclaw-skills-security --skill output-sanitizer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents the accidental leakage of sensitive information, such as credentials, PII, and internal system details, from AI agent responses before they are displayed or logged.

Core Features & Use Cases

Credential Redaction: Automatically detects and masks API keys, passwords, and private keys.
PII Masking: Obscures email addresses, phone numbers, and national IDs.
Internal Path Generalization: Replaces full home directory paths and internal hostnames with generalized placeholders.
Use Case: After an agent performs a code review and might have inadvertently included a hardcoded API key in its output, this skill will redact the key, ensuring it's not exposed to the user or logs.

Quick Start

Sanitize the provided agent output by redacting any sensitive information.

Frequently Asked Questions about output-sanitizer

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

FAQPage Schema

How do I redact API keys and passwords from AI agent output?▼

To redact API keys and passwords from AI agent output, apply pattern-based detection and masking rules to automatically identify and obscure credentials before the response is displayed or logged.

What is output sanitization for AI generated content?▼

Output sanitization for AI generated content is the process of detecting and redacting sensitive information like PII, credentials, and internal system paths to prevent accidental data leakage in agent responses.

How do I mask PII like email addresses and phone numbers in agent responses?▼

You can mask PII like email addresses and phone numbers in agent responses by applying data masking rules that detect specific patterns and obscure the sensitive text securely.

How do I generalize internal system paths and hostnames in AI logs?▼

To generalize internal system paths and hostnames in AI logs, apply redaction rules that replace full home directory paths and internal hostnames with generalized placeholders before logging.

What is the best way to prevent accidental data leakage from AI responses?▼

The best way to prevent accidental data leakage from AI responses is to sanitize the output by detecting and redacting sensitive information including credentials, PII, and internal system paths before display.