ClawHub

奇门遁甲排盘Pro

Security checks across malware telemetry and agentic risk

Overview

This is a local Qimen Dunjia charting and interpretation skill whose code matches its stated purpose and does not show hidden data access or persistence.

Install only if you want a local Node-based divination/charting helper. Treat health, legal, investment, travel, or other decision advice as cultural/reference output rather than authoritative guidance, and confirm separately before using any external Feishu or email tool to share results.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
Overly broad trigger words such as '占卜'、'吉凶'、'吉方' can cause the skill to activate in unrelated conversations, increasing the chance that users are routed into a specialized workflow unexpectedly. In agent environments, accidental invocation can lead to unintended tool execution, confusing outputs, and expanded attack surface if downstream scripts or integrations are automatically available.

Vague Triggers

Low
Confidence
79% confidence
Finding
The example trigger scenarios are broad and lack explicit boundaries, so ordinary discussion about luck, travel, or timing may match the skill unintentionally. While the content is not inherently malicious, ambiguous activation criteria make the skill more likely to run outside user intent, which is a safety and control weakness in an automated agent setting.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal