Skills
.Work. You
Rest

bidirectional-filtering

Official

Implement real-time runtime guardrails for AI input/output safety.

Software Engineering#security#runtime#guardrails#ai-safety#prompt-injection#content-filtering
AuthorRedHatProductSecurity
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides runtime guardrails for AI systems to prevent prompt injection, content leakage, and unsafe responses, ensuring AI interactions remain secure and compliant.

Core Features & Use Cases

  • Content Filtering: Inspects and modifies prompts and responses to enforce safety policies in AI workflows.
  • Prompt Injection Prevention: Detects and blocks potentially dangerous input patterns before they reach the model.
  • Use Case: When designing an AI assistant that handles sensitive data, apply this Skill to block or mask sensitive information and prevent prompt manipulation.

Quick Start

Evaluate and configure guardrails to analyze both prompts and model responses for safer AI deployment.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: bidirectional-filtering
Download link: https://github.com/RedHatProductSecurity/prodsec-skills/archive/main.zip#bidirectional-filtering

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 471,000+ vetted skills library on demand.