io.github.bch1212/injectshield

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

Ready: LocalSecurity: LocalAuth: UnknownSetup: Unknownmcp_servermcp

Use it

Packages
  • npm: @injectshield/mcp 0.1.4npx -y @injectshield/mcp
    Env: INJECTSHIELD_API_KEY, INJECTSHIELD_API_BASE
Instructions
  • Use an MCP client, but no callable endpoint or package install target was published.

Version history

VersionStatusPublished
0.1.4LatestactiveMay 6, 2026