ClawHub
Back to skill

Security audit

亚洲直通车 · 跟 Jessie 看亚洲班课程体系

Security checks across malware telemetry and agentic risk

Overview

This is a school-specific education and curriculum guidance skill with only static informational content and a simple local helper script.

Install this if you want Chinese-language guidance about this school's Asia pathway curriculum. Treat admissions facts, rankings, costs, and deadlines as informational and verify them with current university sources; also expect the skill may activate on fairly general Asia study-abroad or course-consulting questions.

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
84% confidence
Finding
The auto-trigger conditions are broad natural-language phrases such as general study-abroad or course-consultation queries, which can overlap with ordinary user conversations and cause the skill to activate unexpectedly. This can lead to inappropriate context injection, biased responses, or execution of associated commands/workflows when the user did not explicitly request this specific skill.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.