ClawHub
Back to skill

Security audit

Marketing Hooks

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only marketing writing helper with broad activation language but no evidence of system access or hidden behavior.

Safe to install as a content helper. Use it when you want marketing-oriented hooks, specify the target platform and audience, and verify any numbers, income claims, screenshots, timelines, or social-proof statements before publishing.

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 contains broad trigger phrases such as "write a hook," "create a title," and "make this more engaging," which can cause the skill to activate in many unrelated content-generation contexts. Over-broad invocation increases the chance the wrong skill is selected, leading to unintended prompt injection surface expansion and inappropriate application of manipulative marketing guidance where it was not requested.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.