ClawHub
Back to skill

Security audit

基于艾宾浩斯遗忘曲线的英语四级词汇记忆系统

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed vocabulary-study skill that stores study progress locally and can set reminder jobs, with no evidence of hidden or unrelated behavior.

Install only if you want local study tracking and recurring reminders. Before enabling reminders, confirm the exact crontab entries, the OpenClaw account and target user, and how to disable or remove the schedule later.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill instructs the agent to create or modify system crontab entries, which is a persistent system-level action beyond what a vocabulary-learning feature strictly needs. Even if intended for reminders, granting a conversational skill the ability to alter scheduled tasks increases the risk of persistence, misuse, or unintended modification of host scheduling state.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly writes user data to CSV files and sets scheduled tasks, which changes persistent user/system state, but it does not describe any explicit consent, confirmation, or safety boundaries before doing so. This is dangerous because an accidentally triggered or ambiguous invocation could cause unwanted reminders, overwrite schedule data, or persist personal study habits without the user's informed approval.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The workflow says to write user data to a CSV file and install cron jobs, but it does not require a clear warning or explicit consent for these persistent changes. This is dangerous because users may trigger what appears to be a study feature without understanding that it modifies stored data and host scheduling behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.