ClawHub
Back to skill

Security audit

compare-masters

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Buddhist comparison meta-skill that guides cited, non-ranking answers and does not request unusual system access.

Install this for Buddhist doctrinal or historical comparison workflows, not as a general comparison tool. Users should expect it to rely on declared source citations and FoJin-related references, and should verify citations for important religious or scholarly use.

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
92% confidence
Finding
The trigger definition is extremely broad and includes generic comparison terms such as “compare”, “comparison”, “多个角度”, and “对比”, which can cause this meta-skill to activate for many queries that are not actually about Buddhist multi-tradition analysis. Over-triggering can route users into an inappropriate specialized workflow, increasing the risk of incorrect tool selection, irrelevant retrieval, and confusing or policy-bypassing responses in downstream skills.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.