ClawHub
Back to skill

Security audit

Agent Network Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple scanner guide, but it encourages broad internet reconnaissance without clear authorization or scope limits.

Review and constrain this skill before use. Only run it against domains you own or are authorized to assess, set explicit target lists and rate limits, and expect it to contact external websites and DNS services.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill is framed with very broad directives such as 'Find every agent network on the internet' and 'Scan domains' without clear scope, authorization, or user-confirmed targets. In an agent setting, this can cause the skill to be invoked for unrestricted reconnaissance against arbitrary third-party domains, increasing the risk of unauthorized external probing and misuse.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation includes ready-to-run curl/dig loops that make outbound requests to arbitrary domains but does not warn that using the skill will contact external systems. In agent environments, that omission can lead to silent network access, privacy leaks, policy violations, or unintended reconnaissance simply from invoking the skill as documented.

Static analysis

No suspicious patterns detected.