Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Major update: transitions from SDK-based middleware setup to native OpenClaw plugin configuration. - Now installs AI Sentinel via `openclaw plugins install ai-sentinel` instead of direct SDK integration. - Plugin configuration is managed under the OpenClaw `plugins.entries` section, supporting both Community (local) and Pro (dashboard) modes. - Updated steps and consent flow for choosing protection level, detection mode, and (in Pro) reporting/telemetry options. - All file writes and configuration changes require explicit user confirmation. - Clarified data transmission for Pro mode and improved step-by-step integration guidance.
What This Skill Does
Prompt injection firewall for OpenClaw agents. Hooks into gateway lifecycle events to scan inbound messages, tool call parameters, and tool results using heuristic pattern matching. Covers 7 threat categories including jailbreak, data exfiltration, and indirect injection.
Community mode runs entirely locally with no data leaving the machine, so teams get injection protection without transmitting message content to any external service.
When to use it
- Block prompt injection attempts in a public-facing customer support bot
- Audit tool call parameters for data exfiltration patterns before execution
- Monitor agent traffic for jailbreak attempts without blocking in monitor mode
- Enforce message filtering on an agent handling sensitive internal data
- Review threat detection analytics after a suspected attack via the Pro dashboard
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Set up prompt injection protection on my OpenClaw agent
- 1Installs ai-sentinel plugin via openclaw plugins install
- 2Asks user to choose Community (local) or Pro (dashboard reporting) tier
- 3Asks user to set detection mode (monitor or enforce) and confidence threshold
- 4Generates plugin config under plugins.entries.ai-sentinel and writes it to OpenClaw configuration after user confirms
- 5Tests detection by sending a known injection pattern through the gateway and verifying the log output
OpenClaw gateway scanning all lifecycle hooks for prompt injection, with detections logged or blocked based on chosen mode
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.