ClawHub
Back to skill

Security audit

get-public-ip

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it checks the user’s public IP by querying disclosed third-party IP services, with no bundled code, persistence, or credential access.

Install this if you are comfortable with the agent making short outbound requests to the listed IP-check services when you ask for your public IP. Those services may observe your public IP and normal request metadata. The package itself contains no executable installer or persistence mechanism.

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)

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The text says "直接说或写中文即可" and only provides Chinese trigger phrases, which imposes a specific language requirement. Under the policy, forcing a language or locale without user opt-in is a natural-language policy violation unless the constraint is explicitly justified as region-specific.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to contact third-party IP-check services, which necessarily discloses the user's public IP and related metadata to external providers. While this is core to the feature rather than overtly malicious behavior, the lack of an explicit privacy warning or consent mechanism creates a real privacy issue because users may not realize their network information is being shared outside the local system.

Static analysis

No suspicious patterns detected.