ClawHub
Back to skill

Security audit

Myip

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small IP-checking helper whose network and local commands match its stated purpose, with only minor privacy and language-disclosure caveats.

Before installing, confirm you are comfortable using ifconfig.me or api.ipify.org to learn your public IP. In restricted enterprise environments, prefer an approved internal endpoint or ask before running the public-IP step.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to contact third-party IP echo services to obtain the machine's public IP, but it does not clearly disclose that this action sends a network request to an external service and reveals the caller's public IP and request metadata to that service. While this is expected behavior for public-IP discovery and not inherently malicious, it creates an avoidable privacy and data-handling risk, especially in enterprise or restricted environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The package description is written only in Chinese ("一个实用的内外网 IP 查询工具"), which can create a language/locale policy concern if the skill is intended for general use but does not offer user language choice or document a region-specific scope. This is a natural-language policy issue because the file provides a single-language experience without visible opt-in or justification.

Content

No source excerpt is available for this finding.