A security and compliance layer that enforces real-time policy evaluation and human approval for AI tool executions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install sidclaw-governance
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install sidclaw-governance using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is SidClaw Governance?
SidClaw Governance is a robust security framework designed to wrap around AI tool calls, ensuring every action complies with organizational policies before execution. As a premier entry in the Openclaw Skills library, it acts as a gatekeeper that can automatically allow, deny, or pause actions for human review based on predefined security logic.
By integrating this skill, developers can ensure their AI agents operate within safe boundaries, providing a clear audit trail for compliance and security teams. It effectively bridges the gap between autonomous AI capabilities and necessary human oversight, making it indispensable for enterprise-grade AI deployments.
SidClaw Governance Use Cases
- Enforcing security boundaries on sensitive tool calls like data exports or system modifications.
- Implementing human-in-the-loop workflows for high-stakes AI actions.
- Maintaining a comprehensive audit trail of all AI-driven tool executions for regulatory compliance.
- Preventing prompt injection or unauthorized tool usage through centralized policy management.
How SidClaw Governance Works
- When the AI agent attempts to call a tool, the SidClaw policy engine intercepts the request.
- The engine evaluates the call against active security policies based on context and parameters.
- The engine returns one of three statuses: Allowed (immediate execution), Denied (execution blocked), or Approval Required (paused).
- If approval is required, a unique request ID is generated, and the agent prompts the user to review the action in the dashboard.
- Upon user confirmation or policy clearance, the workflow resumes or terminates based on the authoritative governance decision.
SidClaw Governance Setup
To integrate SidClaw Governance into your environment, ensure you have the necessary credentials and the Node.js runtime installed.
# Set required environment variables
export SIDCLAW_API_KEY="your_api_key_here"
export SIDCLAW_AGENT_ID="your_agent_id_here"
# The skill will automatically interface with your Openclaw Skills setup
SidClaw Governance Data Schema & Taxonomy
SidClaw Governance manages structured responses and logs to maintain a secure state. The following data points are central to the Openclaw Skills governance workflow:
| Attribute | Description | Type |
|---|---|---|
approval_request_id |
Unique identifier for a pending human review | String |
type |
The status of the policy evaluation (allowed/denied/approval_required) | String |
reason |
Technical or policy-based justification for the decision | String |
audit_trail |
A complete trace of tool calls and outcomes stored in the dashboard | Log |
metadata |
Includes environment details and agent identifiers | JSON |
SidClaw Governance Advanced Features
- Real-time policy evaluation with zero-latency overhead for allowed actions.
- Multi-agent support where each tool call is evaluated independently across different sessions.
- Centralized Dashboard for managing the Approval Queue and reviewing the Audit Trail.
- Authority-driven responses that prevent agents from circumventing security blocks or retrying denied actions.
- Deep integration with Openclaw Skills for standardized AI-to-tool communication.
SKILL.md
Loading
Related Openclaw Skills
Huawei AppGallery Integration
A specialized skill for extracting and organizing public distribution rules, review guidelines, and developer documentation from the Huawei AppGallery ecosystem.
Handover Sync
A professional documentation-sync skill that generates concrete end-of-session summaries and updates project handoff files based on repository evidence.
JiuJiu Mindmap Summary
A specialized AI skill that converts lengthy text descriptions into structured JSON mindmaps for visual organization.
Nearby Breakfast Spots
A location-aware skill designed to help users discover breakfast, brunch, and coffee spots based on real-time coordinates.
apk-decompiler
A comprehensive Android reverse engineering suite for decompiling, modifying, and repackaging APK files with automated tool management.
gcoord: Geographic Coordinate System Converter
A specialized tool for converting geographic coordinates between WGS84, GCJ02, BD09, and other systems used by Chinese mapping services.
Featured*
