ClawHub
Back to skill

Security audit

中医用理法方药学方剂

Security checks across malware telemetry and agentic risk

Overview

This is a Traditional Chinese Medicine formula study helper with no code or system access requests, but its medical content should be treated as educational only.

Install this only if you want a study aid for TCM formula learning. Do not use it for diagnosis, treatment decisions, prescriptions, dose changes, or real symptoms without a qualified clinician.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill’s trigger conditions are extremely broad, covering generic requests like studying formulas, organizing notes, analyzing mechanisms, or making diagrams. In an agent system, this can cause the skill to activate outside its narrow intended use, leading to misrouting, over-collection of user context, and inappropriate medical-style guidance in conversations that only loosely match the domain.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.