Prompt Guard - AI Skill | Natoma

orchestra-research

Prompt Guard

by @orchestra-research

Type

Instruction

Platforms

Claude CodeClaude.aiAPI

Best for

developersecurity

Resources

Source Repository Author

Prompt Guard

This skill detects prompt injections and jailbreak attempts in LLM apps, ensuring safer interactions and reliable third-party data filtering.

Try it out

Help me use the Prompt Guard skill effectively.

How it works

This skill detects prompt injections and jailbreak attempts in LLM apps, ensuring safer interactions and reliable third-party data filtering.

Tags

aisecuritydatabackendapitesting