ClawHub
Back to skill

Security audit

Lunar Calendar Vietnam

Security checks across malware telemetry and agentic risk

Overview

This is a local Vietnamese lunar-calendar helper with some accuracy and dependency hygiene caveats, but no evidence of hidden data access, persistence, or malicious behavior.

Install only if you want the agent to run a local Node.js calendar calculator for Vietnamese lunar-date questions. Treat lunar-to-solar reverse conversions and fortune/day-quality advice as informational, and prefer lockfile-based installs so the dependency version stays fixed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Intent-Code Divergence

Medium
Confidence
88% confidence
Finding
The reverse conversion logic brute-forces solar dates using `targetYY` as the solar year, even though lunar dates near Tết and leap-month boundaries may map to adjacent Gregorian years. In a calendar-conversion skill, this can silently return incorrect dates, which can mislead users and any automations relying on the output for scheduling, compliance, or historical date interpretation.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The activation guidance is broad enough to match common calendar-related queries, which can cause the skill to trigger when the user did not explicitly want this specialized behavior. In a date-conversion and fortune-guidance skill, overbroad invocation increases the chance of unintended routing and culturally specific advice being injected into otherwise generic calendar requests.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"author": "OpenClaw Team",
  "license": "MIT",
  "dependencies": {
    "minimist": "^1.2.8"
  }
}
Confidence
89% confidence
Finding
"minimist": "^1.2.8"

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.