ClawHub
Back to skill

Security audit

lecture-notes-master

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Obsidian lecture-note generator that writes note files and optional charts as part of its stated purpose, with manageable risks around broad triggers and local file creation.

Before installing, edit config.json to use your own vault path, name, institution, and language preferences. Use a test folder first, review the planned file tree and destination path before allowing writes, and avoid sending private URLs or documents through external extraction/model tools unless you are comfortable with that processing.

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
82% confidence
Finding
The trigger phrases are broad enough to match common requests like 'summarize' or 'create notes,' which can cause the skill to activate in situations where the user did not intend filesystem changes or structured vault generation. In this skill, unintended invocation is more dangerous because activation can lead to directory creation, note generation, and local file writes.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow mandates creating directories and files inside the user's Obsidian vault, but it does not require an explicit user-facing warning or confirmation before modifying local storage. This is dangerous because an automatically invoked skill could make persistent changes, clutter the vault, or overwrite user content without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.