ClawHub
Back to skill

Security audit

Copywriting Cta

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only copywriting skill for designing end-of-article CTAs, with no hidden execution, data collection, persistence, or destructive behavior found.

This skill appears safe to install for CTA writing and review. Be aware that its declared tool list is broader than necessary for a writing aid, so review any proposed file edits before accepting them; the artifacts themselves are coherent and low risk.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
### How to check

- **Browser DevTools:** Chrome and Firefox both ship contrast checkers in the color picker of the inspector.
- **CLI / programmatic:** axe-core, pa11y, Lighthouse.
- **Quick web tools:** WebAIM Contrast Checker, Coolors Contrast Checker, Stark.
Confidence
85% confidence
Finding
Tools:*

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
- **Browser DevTools:** Chrome and Firefox both ship contrast checkers in the color picker of the inspector.
- **CLI / programmatic:** axe-core, pa11y, Lighthouse.
- **Quick web tools:** WebAIM Contrast Checker, Coolors Contrast Checker, Stark.

---
Confidence
85% confidence
Finding
tools:*

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.