This skill defends AI agents against prompt injection by detecting and blocking suspicious inputs with offline 577-pattern defense and optional API access.
npx playbooks add skill seojoonkim/prompt-guard --skill prompt-guard
Prompt Guard specializes your AI coding agent in security — it this skill defends ai agents against prompt injection by detecting and blocking suspicious inputs with offline 577-pattern defense and optional api access.
At 22 words, this compact prompt gives your agent specialized security expertise with structured patterns and output formats. Install via CLI or copy the prompt below.
This skill defends AI agents against prompt injection by detecting and blocking suspicious inputs with offline 577-pattern defense and optional API access.
Prompt Guard is a free security skill for AI coding agents. This skill defends AI agents against prompt injection by detecting and blocking suspicious inputs with offline 577-pattern defense and optional API access.. It provides a specialized system prompt that configures your agent with security expertise.
Run npx playbooks add skill seojoonkim/prompt-guard --skill prompt-guard in your terminal to install Prompt Guard into your Claude Code session. It works immediately after installation.
Prompt Guard is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Yes, Prompt Guard is completely free and open source. The full source is available on GitHub at https://github.com/seojoonkim/prompt-guard/tree/main/SKILL.md. You only need a subscription to the AI agent you use it with.
Weekly roundup of top Claude Code skills, MCP servers, and AI coding tips.