ClawHub
Back to skill

Security audit

Grade English Homework (3-6)

Security checks across malware telemetry and agentic risk

Overview

This is a simple English-homework grading prompt with no code execution, persistence, credential use, or hidden data handling.

Installers should expect this skill to format feedback in Chinese and focus on grades 3-6 English homework. It may be triggered by broad correction phrases, so users should be clear when they want a different kind of English review.

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 (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger list includes broad phrases such as '改错' and 'check my English', which can match many ordinary requests outside the narrow scope of elementary-school English homework grading. This can cause unintended skill activation, routing unrelated user content into this grading workflow and producing inappropriate or misleading responses.

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The prompt requires feedback in Chinese with no user-language fallback or explicit consent, which can lead to incorrect or inaccessible output for users who are not Chinese speakers or who requested English feedback. In a prompt-routing system, this is a reliability and UX safety issue because it may disregard user intent and reduce the usefulness of the response.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.