ClawHub
Back to skill

Security audit

Viral Hook Weaponizer

Security checks across malware telemetry and agentic risk

Overview

This is a text-only skill for generating short viral-content hooks, with no code, installation scripts, credentials, persistence, or hidden data access.

Before installing, understand that this skill may activate for broad content-engagement requests and will produce persuasive marketing-style hooks. Review outputs for accuracy, avoid deceptive claims or sensitive targeting, and make sure generated hooks comply with platform and advertising rules.

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
90% confidence
Finding
The trigger conditions are broad enough to activate on common requests for content ideas, captions, or engagement help, which can cause this skill to hijack unrelated user workflows. Overly generic activation increases the chance of unintended invocation and can lead to misrouting, inappropriate outputs, or interference with more suitable specialized skills.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.