Verified record · from the answer index

io.github.bch1212/injectshield

mcptested · static-verifiedscore 41/100signed passport ✓published 71d ago · verified 2026-07-110 GitHub stars

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

Install

claude mcp add injectshield -- npx -y @injectshield/mcp

registry:io.github.bch1212/injectshield · published by bch1212 · source repository