network-watcher

Audit OpenClaw skill network requests for data exfiltration and unauthorized calls.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/wongdean/knowledge-base --skill network-watcher-wongdean
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: network-watcher
Source: https://github.com/wongdean/knowledge-base/tree/main/backups/openclaw-config/20260315_232439/workspace-skills/openclaw-skills-security/skills/network-watcher
Command: npx skills add https://github.com/wongdean/knowledge-base --skill network-watcher-wongdean

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill acts as a network security auditor, scrutinizing network requests made by OpenClaw skills to prevent data exfiltration and unauthorized outbound access.

Core Features & Use Cases

  • Network Request Auditing: Analyzes destinations, ports, and data egress patterns.
  • Exfiltration Detection: Identifies suspicious outbound connections and data leakage attempts.
  • Use Case: Before installing a new OpenClaw skill that requires network access, use this Skill to audit its declared endpoints and identify any potential security risks like connections to raw IP addresses or attempts to send sensitive data via DNS queries.

Quick Start

Audit the network activity of the 'data-processor' skill before granting it network permission.

Frequently Asked Questions about network-watcher

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit outbound connections in OpenClaw skills to prevent data exfiltration?

You audit outbound connections by analyzing destination endpoints, ports, and data egress patterns to identify unauthorized API calls and data exfiltration attempts. The network-audit module applies exfiltration heuristics and explicit safe-pattern checks to detect suspicious activity.

What is data exfiltration detection for API security and how does it work?

Data exfiltration detection scrutinizes network requests to identify data leakage attempts like sending sensitive data via DNS queries or raw IP connections. It evaluates request destinations, tunneling patterns, and data egress risk using endpoint scrutiny and behavioral heuristics.

How can I check an OpenClaw skill for unauthorized API calls before installing it?

You check for unauthorized API calls by auditing the skill's declared network endpoints before granting permissions. This process reviews destinations, ports, and tunneling patterns to identify potential security risks like suspicious outbound connections.

Does the network-audit module detect DNS tunneling patterns and raw IP connections?

Yes, the network-audit module detects DNS tunneling patterns and raw IP connections. It reviews destinations, ports, and data egress risk using endpoint scrutiny and exfiltration heuristics to flag these suspicious outbound activities.

What are the limitations of using exfiltration heuristics for network security auditing?

Exfiltration heuristics rely on endpoint scrutiny and explicit safe-pattern checks, meaning they may flag unknown but benign destinations as suspicious. Auditing focuses on declared endpoints and outbound connection patterns rather than decrypting or inspecting encrypted payload contents.