ClawHub
Back to skill

Security audit

Copywriting

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only copywriting guide that is aligned with its stated marketing-writing purpose and does not request system access or execute code.

Safe to install as a marketing-writing assistant. Be aware it may activate on broad headline-writing prompts, and review any generated scarcity, urgency, statistics, testimonials, ROI, or credential claims for accuracy and fairness 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
92% confidence
Finding
The trigger description is overly broad and includes generic phrases like "headline" and "how to write [marketing text]," which can cause the skill to activate for ordinary writing requests beyond persuasive marketing use. This increases the chance of inappropriate routing, where a persuasion-focused skill is invoked in contexts that did not intend marketing or behavioral influence.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.