ClawHub
Back to skill

Security audit

Content Goldmine

Security checks across malware telemetry and agentic risk

Overview

This writing-analysis skill is coherent and only contains Markdown instructions, though users should approve any note-saving before it writes to an Obsidian vault or material library.

Install only if you want an article-decomposition workflow that can produce reusable notes. Before saving anything, choose the folder or vault yourself, review the filename and content, and avoid storing confidential or copyrighted source material unless you intentionally want it retained.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The skill extends from passive article analysis into persistent file modification by directing results to be saved into the user's material library or Obsidian vault. That creates an integrity risk because the skill can cause side effects on user files without an explicit consent/confirmation boundary tied to each write operation.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The activation criteria are very broad and can trigger on common writing-help requests, increasing the chance the skill runs when the user did not intend a structured decomposition workflow or associated persistence behavior. In context, this becomes more dangerous because an over-triggered skill may perform unexpected analysis or lead into unexpected file-saving actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs saving outputs into the user's Obsidian vault without a user-facing warning or explicit consent flow for modifying files. This is dangerous because users may expect analysis only, while the skill introduces silent persistence into personal knowledge-base files, risking unwanted writes, clutter, or overwriting adjacent content if implemented loosely.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.