Security audit

Easy English Tool 英语学习速通工具

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent for English learning, but it asks agents to handle login credentials and personal learning data with a remote service without enough upfront consent and scoping.

Review this before installing if you are comfortable connecting an agent to english.geeyo.com and letting it use account credentials, user IDs, learning history, and study actions. Prefer explicit confirmation before login, profile/history reads, article deletion, quiz submission, or other changes to your account data.

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 (2)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger list includes broad everyday phrases such as 'study English', 'my vocab', and 'my progress' without clear scoping or consent boundaries. This can cause the skill to activate in ordinary conversations and route user requests, learning data, or follow-on actions to a remote third-party service unexpectedly.

Missing User Warnings

High

Confidence: 97% confidence
Finding: The skill explicitly handles usernames, passwords, user IDs, and personal learning history via a remote service, but it does not prominently warn that these credentials and user data are transmitted to a third-party server. This creates a meaningful privacy and credential-handling risk because users may provide sensitive information without informed consent.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.