ClawHub
Back to skill

Security audit

Content Strategy

Security checks across malware telemetry and agentic risk

Overview

This is a content-marketing planning guide with no executable code or hidden behavior; the only notable issues are broad activation wording and normal privacy caution around business/customer material.

Safe to install as a planning guide. Keep publishing, email sends, and direct messages under your explicit control, and avoid pasting raw customer names, emails, transcripts, or sensitive business records unless you have permission and a clear need.

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
92% confidence
Finding
The trigger list includes very broad, common phrases such as "content ideas," "content plan," and "what content should I create," which can match many ordinary user requests beyond the narrow intent of this skill. This can cause unintended activation, routing users into this skill when another skill or a general assistant response would be more appropriate, increasing the chance of incorrect task execution or confused tool behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.