ClawHub
Back to skill

Security audit

study-abroad-advisor

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only study-abroad advising skill with no install code or hidden data access, though users should remove the default WeChat contact from generated presentations if they do not want it included.

Install only if you want an admissions-planning and presentation-drafting aid. Do not share more applicant details than needed, verify current admissions policies independently, and remove or replace the default WeChat contact before exporting or sharing any PPT.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation keywords are extremely broad terms like '留学', '选校', and '文书', which can match ordinary conversation and trigger the skill unintentionally. Over-broad triggering can route unrelated user content into this skill, causing unexpected behavior, privacy issues, or undesired tool invocation such as automatic PPT generation in contexts the user did not clearly request.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The problem-type triggers are vague patterns such as '我的条件' or '应该怎么准备', which are common in many benign conversations and lack clear activation boundaries. This ambiguity increases the chance of accidental activation and misclassification, which can lead the assistant to apply the wrong workflow or produce sensitive outputs without clear user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill hard-codes personal contact information into generated PPT output, causing disclosure of third-party personal data regardless of user need or consent. If the skill is widely used, this creates avoidable privacy exposure and may also facilitate unsolicited contact, scraping, or social engineering against the individual whose contact details are embedded.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.