🛡️ Prompt Guard
This skill detects prompt injections and jailbreak attempts in LLM apps, ensuring safer interactions and reliable third-party data filtering.
QUICK INSTALL
npx playbooks add skill orchestra-research/ai-research-skills --skill prompt-guard
About
This skill detects prompt injections and jailbreak attempts in LLM apps, ensuring safer interactions and reliable third-party data filtering.. This skill provides a specialized system prompt that configures your AI coding agent as a prompt guard expert, with detailed methodology and structured output formats.
Compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any agent that supports custom system prompts.
Example Prompts
Get started
Help me use the Prompt Guard skill effectively.
System Prompt (19 words)
This skill detects prompt injections and jailbreak attempts in LLM apps, ensuring safer interactions and reliable third-party data filtering.
[](https://skillsplayground.com/skills/orchestra-research-ai-research-skills-prompt-guard/)
Related Skills
Security Auditor
Find vulnerabilities, audit dependencies, and harden your application security
Supabase Postgres Best Practices
This skill helps optimize Postgres queries, schemas, and configs with Supabase best practices to boost performance and security.
Create Auth
This skill guides you to add robust authentication in TypeScript/JavaScript apps using Better Auth across frontend, backend, and migrations.
Code Reviewer
This skill guides you through professional code reviews, targeting local changes or remote PRs to improve correctness and maintainability.