🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
πŸ¦€ ClawHub

Operation Quarantine

by @dank-varley

Prompt injection defense for OpenClaw agents. Scans emails and skill installations through a two-phase security pipeline (pattern matching + optional LLM ana...

Versionv1.0.3
πŸ’‘ Examples

cd service
npm install --production
cp .env.example .env   # edit .env with your settings
node server.js

The service binds to 127.0.0.1 (localhost only) by default. No external network access is required or enabled unless you explicitly opt in.

βš™οΈ Configuration

Configuration lives in service/.env. Key settings:

  • QUARANTINE_PORT β€” Service port (default 8085)
  • QUARANTINE_BIND_HOST β€” Bind address (default 127.0.0.1, localhost only)
  • QUARANTINE_ALERT_THRESHOLD β€” Score to flag as suspicious (default 20)
  • QUARANTINE_BLOCK_THRESHOLD β€” Score to block entirely (default 50)
  • QUARANTINE_ENABLE_LLM β€” Enable LLM second pass (true/false)
  • QUARANTINE_ALERT_MODE β€” Alert delivery: openclaw, custom, or none (default: none)
  • ENABLE_WEBHOOKS β€” Set to 1 to allow external network egress for custom alerts (default: off)
  • View on ClawHub
    TERMINAL
    clawhub install operation-quarantine

    πŸ§ͺ Use this skill with your agent

    Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.

    πŸ” Can't find the right skill?

    Search 60,000+ AI agent skills β€” free, no login needed.

    Search Skills β†’