ClawHub

ADS-B Overhead

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed aircraft-alert watcher that reads a local ADS-B feed, optionally enriches aircraft data, and sends configured WhatsApp notifications.

Before installing, confirm the SBS host, home coordinates, radius, cooldown, photo setting, and WhatsApp target. Keep the config private because it can reveal a home location and phone number, and remove the cron entry or disable the config when you no longer want continuous monitoring.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation describes shell execution, TCP connectivity to a local SBS feed, and persistence to a JSON state file, yet no permissions are declared. That creates an authorization and review gap: operators may approve or run the skill without understanding that it can read/write local files, open network connections, and invoke commands, which increases the chance of unintended access or misuse.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The documented purpose is limited to consuming a local ADS-B feed and sending nearby-aircraft alerts, but the actual behavior reportedly includes external HTTP enrichment, third-party API queries, local image downloads, and outbound tracking links that are not disclosed. This mismatch is dangerous because it hides additional data flows and storage behaviors from reviewers and users, undermining informed consent and making exfiltration, privacy leakage, and unexpected network/file activity harder to detect.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal