ClawHub
Back to skill

Security audit

study-workbench

Security checks across malware telemetry and agentic risk

Overview

This skill coherently builds a local student study-workbench HTML page and does not show hidden data collection, credential access, or destructive behavior.

Install this if you want a local/offline learning workbench generator. Be aware that broad education prompts may invoke it unexpectedly, and only use content packs or optional textbook links from sources you trust because generated pages will render that content and store progress in your browser.

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
92% confidence
Finding
The trigger phrases are generic enough to overlap with normal educational conversation, which can cause the skill to activate when the user did not explicitly intend to invoke it. In an agent environment, unintended invocation can redirect user workflows, produce unexpected files or content, and increase the chance of prompt-routing abuse or accidental execution of skill logic.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases include very generic terms such as '课程表', '备考', 'xx年级', and 'xx科', which can match broad everyday educational requests beyond the intended narrow use case. Overly broad activation increases the chance the wrong skill is invoked, causing unintended file generation, confusion, or unsafe tool chaining if this skill is selected when a more appropriate skill should handle the request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.