ClawHub
Back to skill

Security audit

ip-query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward public IP lookup tool that discloses its third-party API use and does not show hidden persistence, credential access, or destructive behavior.

Install only if you are comfortable with the tool contacting public IP lookup providers; detailed and JSON modes may reveal approximate location, ISP, and organization data to or from ipinfo.io. Prefer simple mode if you only need the public IP address.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script contacts multiple third-party services and transmits/derives the user's public IP and, in detailed mode, retrieves associated location and network metadata. This is a real privacy issue because users are not clearly warned in the help/usage text that running the tool discloses information to external providers and may return sensitive geolocation/ISP details.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The script's comments, help text, status messages, and output are all written in Chinese, and there is no option to select another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific.

Missing User Warnings

Low
Confidence
80% confidence
Finding
This code file runs `./ip_query.sh` multiple times, which is a subprocess execution covered by the missing user warnings rule. While the script prints test-step labels, it does not disclose what `ip_query.sh` will do, whether it may make network requests, or prompt the user before executing it.

Static analysis

No suspicious patterns detected.