ClawHub
Back to skill

Security audit

Course Study

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only study-notes skill whose file, web, PDF, and PDF-export behavior is disclosed and fits its education purpose.

Install this if you want an agent to process course materials into study notes. Expect it to read the course files you provide through the /pdf workflow, optionally search the web for syllabus or supplement sources when available, and create local study-note files in the chosen output folder.

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description includes highly generic invocation examples such as "revise these slides," which overlaps with normal educational chat requests and could cause unintended skill activation. This is dangerous because broad trigger phrasing can route user content into this skill when the user did not explicitly intend to invoke it, increasing the chance of inappropriate tool use, unexpected file processing, or bypass of user expectations about how their request will be handled.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.