Ham Radio DX Monitor

• Outcome: Pass
• Latest audit: May 27, 2026, 9:23 PM
• Version:
  1.0.0

Overview

This skill appears to perform the advertised ham-radio DX monitoring, with disclosed network checks and optional user-configured automation.

Install this only if you want the agent to contact DX cluster servers and possibly send your callsign to them. Add the cron entries only if you want ongoing background monitoring, periodically review or remove the /tmp logs/state file, and do not run any setup script that is not included in the package unless you inspect it separately.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: The example prompts are generic enough that normal conversation such as asking what is active on a band or checking for new spots could unintentionally invoke the skill. Ambiguous activation increases the chance of unexpected network access or state changes without clear user intent.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill encourages cron-based monitoring, logging, and Telegram-style notifications, but does not clearly warn users that it will perform recurring network connections and may disclose callsigns, spot data, or monitoring results to external services. This can lead to unanticipated background activity and data exposure.

Missing User Warnings

Low

• Confidence: 87% confidence
• Finding: The program stores persistent state in a predictable world-writable temporary directory path (/tmp/dx-monitor-state.json). On multi-user systems this can expose usage history, allow tampering, or enable symlink/race attacks that overwrite or read unintended files under the user's permissions.

VirusTotal

64/64 vendors flagged this skill as clean.