prompt-guard

What problem does it solve?

Prompt Guard protects AI agents from prompt injection and secret-exfiltration attempts by providing multi-language detection, decoding pipelines, and enterprise-grade DLP.

Core Features & Use Cases

• SHIELD.md compliant threat classification and decision outputs for automated protection in production.
• HiveFence network integration for threat intelligence sharing and rapid pattern updates.
• Multi-language coverage across EN, KO, JA, ZH, RU, ES, DE, FR, PT, VI for pervasive attacks.
• Use Case: Operators deploy Prompt Guard to guard a group assistant, block dangerous prompts like “ignore previous instructions,” and redact credentials in LLM outputs.

Quick Start

To get started, run a prompt-guard scan on a user message to determine if it should be allowed or blocked.