ClawHub
Back to skill

Security audit

Public IP Watch

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: checks the public IP address, compares it with a small local cache, and reports whether it changed.

Install only if you are comfortable with the agent making outbound requests to public IP-check services and storing the last observed IP in ~/.public_ip_cache.json. If using it in scheduled automation, keep the schedule explicit and avoid triggering it from vague network-status comments unless that is what you intend.

SkillSpector

By NVIDIA
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
82% confidence
Finding
The trigger section includes broad natural-language cues such as '网络断了又好了' that could match many unrelated user situations and cause the skill to run when the user did not explicitly request an external IP check. In this skill, overbroad activation is risky because execution performs outbound network requests and reads/writes a local cache file, so unintended invocation can create privacy and behavior surprises.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to query third-party services (ip.sb and ipinfo.io) but does not clearly disclose this data flow to the user. Even though only the user's public IP is being queried, the request exposes metadata to external providers and may violate user expectations, privacy requirements, or restricted-network policies if invoked silently.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.