ClawHub
Back to skill

Security audit

Package Tracker

Security checks across malware telemetry and agentic risk

Overview

This skill is low-risk to run locally, but it presents made-up demo shipment statuses as real package tracking.

Install only if you want a local demo or tracking-number format simulator. Do not rely on its status, timeline, or estimated delivery date as real carrier information unless the skill is changed to use official carrier APIs and clearly reports when live data is unavailable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The skill advertises real-time worldwide package tracking across many carriers, but the analysis indicates it only produces simulated timelines, supports a limited hardcoded subset, and does not query live carrier services. This is dangerous because it can mislead users into trusting fabricated shipment status, which may cause operational mistakes, privacy over-sharing, or social-engineering opportunities when users act on false delivery information.

Description-Behavior Mismatch

Medium
Confidence
97% confidence
Finding
The skill advertises real package tracking, but the implementation only fabricates shipment events and estimated delivery information. This is dangerous because users may rely on false logistics data for time-sensitive or financial decisions, and the mismatch between advertised behavior and actual behavior is a deceptive integrity issue.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The module docstring and surrounding implementation imply multi-carrier shipment tracking, but the code only detects carrier patterns and returns synthetic tracking timelines. In the context of a package-tracking skill, this increases risk because the core trust model depends on accuracy, and misleading users about live tracking status can cause operational confusion and loss of trust.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.